The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level

• URL: http://arxiv.org/abs/2604.02178v1
• Date: Thu, 02 Apr 2026 15:41:24 GMT
• Title: The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
• Abstract summary: Mixture-of-Experts (MoE) have become the dominant choice for scaling Large Language Models (LLMs)<n>We compare MoE experts and dense feed-forward networks using $k$-sparse probing.<n>We find that expert neurons are consistently less polysemantic, with the gap widening as routing becomes sparser.
• Score: 9.716523835964045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency, it remains an open question whether their sparsity makes them inherently easier to interpret than dense feed-forward networks (FFNs). We compare MoE experts and dense FFNs using $k$-sparse probing and find that expert neurons are consistently less polysemantic, with the gap widening as routing becomes sparser. This suggests that sparsity pressures both individual neurons and entire experts toward monosemanticity. Leveraging this finding, we zoom out from the neuron to the expert level as a more effective unit of analysis. We validate this approach by automatically interpreting hundreds of experts. This analysis allows us to resolve the debate on specialization: experts are neither broad domain specialists (e.g., biology) nor simple token-level processors. Instead, they function as fine-grained task experts, specializing in linguistic operations or semantic tasks (e.g., closing brackets in LaTeX). Our findings suggest that MoEs are inherently interpretable at the expert level, providing a clearer path toward large-scale model interpretability. Code is available at: https://github.com/jerryy33/MoE_analysis

Related papers

• Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs [54.95810313530111]
  DERN is a task-agnostic and retraining-free framework for expert pruning and reconstruction.<n>It improves performance by more than 5% on commonsense reasoning and MMLU benchmarks under 50% expert sparsity.
  arXiv  Detail & Related papers  (2025-09-12T16:09:39Z)
• Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning [76.10639521319382]
  We propose Symbolic-MoE, a symbolic, text-based, and gradient-free Mixture-of-Experts framework.<n>We show Symbolic-MoE beats strong LLMs like GPT4o-mini, as well as multi-agent approaches, with an absolute avg. gain of 8.15% over the best multi-agent baseline.
  arXiv  Detail & Related papers  (2025-03-07T18:03:13Z)
• 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)
• Monet: Mixture of Monosemantic Experts for Transformers [33.8311330578753]
  We introduce Mixture of Monosemantic Experts for Transformers (Monet) architecture.<n>Monet incorporates sparse dictionary learning directly into end-to-end Mixture-of-Experts pretraining.<n>Our analyses demonstrate mutual exclusivity of knowledge across experts and showcase the parametric knowledge encapsulated within individual experts.
  arXiv  Detail & Related papers  (2024-12-05T13:06:03Z)
• Mixture of Parrots: Experts improve memorization more than reasoning [72.445819694797]
  We show that as we increase the number of experts, the memorization performance consistently increases while the reasoning capabilities saturate.<n>We find that increasing the number of experts helps solve knowledge-intensive tasks, but fails to yield the same benefits for reasoning tasks.
  arXiv  Detail & Related papers  (2024-10-24T17:54:41Z)
• Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts [44.09546603624385]
  We introduce a notion of expert specialization for Soft MoE. We show that when there are many small experts, the architecture is implicitly biased in a fashion that allows us to efficiently approximate the specialized expert subset.
  arXiv  Detail & Related papers  (2024-09-02T00:39:00Z)
• Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study [65.11303133775857]
  Mixture-of-Experts (MoE) computation amalgamates predictions from several specialized sub-models (referred to as experts) Sparse MoE selectively engages only a limited number, or even just one expert, significantly reducing overhead while empirically preserving, and sometimes even enhancing, performance.
  arXiv  Detail & Related papers  (2024-03-26T05:48:02Z)
• Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization [51.98792406392873]
  Mixture of Experts (MoE) provides a powerful way to decompose dense layers into smaller, modular computations. A major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. We propose the Multilinear Mixture of Experts ($mu$MoE) layer to address this, focusing on vision models.
  arXiv  Detail & Related papers  (2024-02-19T21:20:22Z)
• MoEC: Mixture of Expert Clusters [93.63738535295866]
  Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation.
  arXiv  Detail & Related papers  (2022-07-19T06:09:55Z)
• Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability [3.021134753248103]
  Sparsely-gated Mixture of Expert (MoE) layers have been successfully applied for scaling large transformers. In this work, we apply sparse MoE layers to CNNs for computer vision tasks and analyze the resulting effect on model interpretability.
  arXiv  Detail & Related papers  (2022-04-22T09:40:23Z)

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.