nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers

• URL: http://arxiv.org/abs/2511.14465v1
• Date: Tue, 18 Nov 2025 13:05:02 GMT
• Title: nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
• Abstract summary: nnterp is a lightweight wrapper around NNsight for transformer analysis.<n>It provides a unified interface for transformer analysis while preserving original HuggingFace implementations.
• Score: 1.0152838128195467
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mechanistic interpretability research requires reliable tools for analyzing transformer internals across diverse architectures. Current approaches face a fundamental tradeoff: custom implementations like TransformerLens ensure consistent interfaces but require coding a manual adaptation for each architecture, introducing numerical mismatch with the original models, while direct HuggingFace access through NNsight preserves exact behavior but lacks standardization across models. To bridge this gap, we develop nnterp, a lightweight wrapper around NNsight that provides a unified interface for transformer analysis while preserving original HuggingFace implementations. Through automatic module renaming and comprehensive validation testing, nnterp enables researchers to write intervention code once and deploy it across 50+ model variants spanning 16 architecture families. The library includes built-in implementations of common interpretability methods (logit lens, patchscope, activation steering) and provides direct access to attention probabilities for models that support it. By packaging validation tests with the library, researchers can verify compatibility with custom models locally. nnterp bridges the gap between correctness and usability in mechanistic interpretability tooling.

Related papers

• Gatekeepers and Hallucinations: A Layered Evaluation Framework for LLM-Driven Quantum Circuit Generation [0.0]
  We present a layered evaluation framework for materials-informed Variational Quantum Eigensolver (VQE) circuit generation.<n>We surface a taxonomy of five distinct LLM failure modes (geometry hallucination, nonexistent API usage, integration failures, constraint violations, and plausible-but-unverifiable output)<n>A forensic audit of the evaluation platform's own source code further establishes that two apparent model failures originated in the harness through silent fallback-template substitution.
  arXiv  Detail & Related papers  (2026-06-16T19:17:54Z)
• One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability [2.550140611921313]
  We present WorldModelLens, an open-source interpretability substrate organized around a capability-typed adapter.<n>Every model implements four required methods (encode, transition, initial state, sample) and declares a set of optional heads.<n>A single hook and cache layer exposes time-indexed activations, imagination rollouts, and intervention replay over this interface.
  arXiv  Detail & Related papers  (2026-06-07T19:27:04Z)
• Weight Patching: Toward Source-Level Mechanistic Localization in LLMs [12.558998651017374]
  We propose Weight Patching, a parameter-space intervention method for source-oriented analysis in paired same-architecture models.<n>We introduce a framework centered on a vector-anchor behavioral interface that provides a shared internal criterion for whether a task-relevant control state has been formed.
  arXiv  Detail & Related papers  (2026-04-15T10:21:38Z)
• CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs [13.488544043942495]
  We aim to investigate whether the model's neural dynamics encode internally decodable signals that are predictive of logical validity during code generation.<n>By decomposing complex residual flows, we aim to identify the structural signatures that distinguish sound reasoning from logical failure.<n>Analysis across Python, C++, and Java confirms that intrinsic correctness signals are robust across diverse syntaxes.
  arXiv  Detail & Related papers  (2026-02-06T03:49:15Z)
• SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks [0.0]
  We present SALVE, a framework that bridges mechanistic interpretability and model editing.<n>We learn a sparse, model-native feature basis without supervision.<n>We validate these features with Grad-FAM, a feature-level saliency mapping method.
  arXiv  Detail & Related papers  (2025-12-17T20:06:03Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [57.19302613163439]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Generalize Your Face Forgery Detectors: An Insertable Adaptation Module Is All You Need [3.5424095074777533]
  We introduce an insertable adaptation module that can adapt a trained off-the-shelf detector using only online unlabeled test data.<n> Specifically, we first present a learnable class prototype-based classifier that generates predictions from the revised features and prototypes.<n>We also propose a nearest feature calibrator to further improve prediction accuracy and reduce the impact of noisy pseudo-labels during self-training.
  arXiv  Detail & Related papers  (2024-12-30T08:48:04Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• Switchable Representation Learning Framework with Self-compatibility [50.48336074436792]
  We propose a Switchable representation learning Framework with Self-Compatibility (SFSC) SFSC generates a series of compatible sub-models with different capacities through one training process. SFSC achieves state-of-the-art performance on the evaluated datasets.
  arXiv  Detail & Related papers  (2022-06-16T16:46:32Z)
• Slimmable Domain Adaptation [112.19652651687402]
  We introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank. Our framework surpasses other competing approaches by a very large margin on multiple benchmarks.
  arXiv  Detail & Related papers  (2022-06-14T06:28:04Z)
• DirectDebug: Automated Testing and Debugging of Feature Models [55.41644538483948]
  Variability models (e.g., feature models) are a common way for the representation of variabilities and commonalities of software artifacts. Complex and often large-scale feature models can become faulty, i.e., do not represent the expected variability properties of the underlying software artifact.
  arXiv  Detail & Related papers  (2021-02-11T11:22:20Z)
• End-to-End Object Detection with Transformers [88.06357745922716]
  We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
  arXiv  Detail & Related papers  (2020-05-26T17:06:38Z)

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.