Sparsity and Superposition in Mixture of Experts

• URL: http://arxiv.org/abs/2510.23671v1
• Date: Sun, 26 Oct 2025 22:44:35 GMT
• Title: Sparsity and Superposition in Mixture of Experts
• Authors: Marmik Chaudhari, Jeremi Nuer, Rome Thorstenson,
• Abstract summary: We show that MoE models cannot be explained mechanistically through the same lens.<n>We find that neither feature sparsity nor feature importance cause discontinuous phase changes.<n>We propose a new definition of expert specialization based on monosemantic feature representation rather than load balancing.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture of Experts (MoE) models have become central to scaling large language models, yet their mechanistic differences from dense networks remain poorly understood. Previous work has explored how dense models use \textit{superposition} to represent more features than dimensions, and how superposition is a function of feature sparsity and feature importance. MoE models cannot be explained mechanistically through the same lens. We find that neither feature sparsity nor feature importance cause discontinuous phase changes, and that network sparsity (the ratio of active to total experts) better characterizes MoEs. We develop new metrics for measuring superposition across experts. Our findings demonstrate that models with greater network sparsity exhibit greater \emph{monosemanticity}. We propose a new definition of expert specialization based on monosemantic feature representation rather than load balancing, showing that experts naturally organize around coherent feature combinations when initialized appropriately. These results suggest that network sparsity in MoEs may enable more interpretable models without sacrificing performance, challenging the common assumption that interpretability and capability are fundamentally at odds.

Related papers

• Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity [45.48194499967696]
  We propose a novel framework that seamlessly balances interpretability and accuracy.<n>Neural Additive Experts (NAEs) employ a mixture of experts framework, learning multiple specialized networks per feature.<n>We show that NAEs achieve an optimal balance between predictive accuracy and transparent, feature-level explanations.
  arXiv  Detail & Related papers  (2026-02-11T07:19:25Z)
• Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization [0.0]
  We study MoE behavior in an image classification setting, focusing on predictive performance, expert utilization, and generalization.<n>We compare dense, SoftMoE, and SparseMoE classifier heads on the CIFAR10 dataset under comparable model capacity.<n>Both MoE variants achieve slightly higher validation accuracy than the dense baseline while maintaining balanced expert utilization through regularization.<n>We find that SoftMoE exhibits higher sharpness by these metrics, while Dense and SparseMoE lie in a similar curvature regime, despite all models achieving comparable generalization performance.
  arXiv  Detail & Related papers  (2026-01-21T14:22:25Z)
• Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder [59.89996751196727]
  Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models.<n>SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs.<n>Recent Mixture of Experts (MoE) approaches attempt to address this by SAEs into narrower expert networks with gated activation.<n>We propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling.
  arXiv  Detail & Related papers  (2025-11-07T22:19:34Z)
• Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization [60.309915093470416]
  Matryoshka MoE (M-MoE) is a training framework that instills a coarse-to-fine structure directly into the expert ensemble.<n>Our work paves the way for more practical and adaptable deployments of large-scale MoE models.
  arXiv  Detail & Related papers  (2025-09-30T16:56:44Z)
• Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms [55.1784306456972]
  Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference.<n>We use an internal metric to investigate the mechanisms of MoE architecture by explicitly incorporating routing mechanisms and analyzing expert-level behaviors.<n>We uncover several findings: (1) neuron utilization decreases as models evolve, reflecting stronger generalization; (2) training exhibits a dynamic trajectory, where benchmark performance alone provides limited signal; (3) task completion emerges from collaborative contributions of multiple experts, with shared experts driving concentration; and (4) activation patterns at the neuron level provide a fine-grained proxy for data diversity.
  arXiv  Detail & Related papers  (2025-09-28T15:13:38Z)
• Mixture of Experts Made Intrinsically Interpretable [34.36996159677674]
  We present textbfMoE-X, a Mixture-of-Experts (MoE) language model designed to be emphintrinsically interpretable.<n>Our approach is motivated by the observation that, in language models, wider networks with sparse activations are more likely to capture interpretable factors.<n>MoE-X achieves perplexity better than GPT-2, with interpretability surpassing even sparse autoencoder (SAE)-based approaches.
  arXiv  Detail & Related papers  (2025-03-05T17:40:54Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.<n>DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast [58.98411447739218]
  Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. We propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding.
  arXiv  Detail & Related papers  (2024-05-23T12:45:29Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• On the Adversarial Robustness of Mixture of Experts [30.028035734576005]
  Recently, Bubeck and Sellke proved a lower bound on the Lipschitz constant of functions that fit the training data in terms of their number of parameters. This raises an interesting open question, do -- and can -- functions with more parameters, but not necessarily more computational cost, have better robustness? We study this question for sparse Mixture of Expert models (MoEs) that make it possible to scale up the model size for a roughly constant computational cost.
  arXiv  Detail & Related papers  (2022-10-19T02:24:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.