Language models can explain neurons in language models

Language Model Circuits Are Sparse in the Neuron Basis

arXiv:2601. 22594v2 Announce Type: replace-cross Abstract: The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986).

Scaling laws for neural language models

Explaining Attention with Program Synthesis

A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper, we propose an approach for approximating the behavior of components of deep networks with executable programs.

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

arXiv:2507. 00322v2 Announce Type: replace-cross Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses.

Explaining Attention with Program Synthesis

arXiv:2606. 19317v1 Announce Type: cross Abstract: A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions.

Evaluating large language models trained on code

XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models

arXiv:2606. 16137v1 Announce Type: cross Abstract: Speech deepfake detection (SDD) systems require trustworthy explanations for reliable decision-making.

What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs

arXiv:2606. 28615v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs.

From Mechanistic to Compositional Interpretability

arXiv:2605. 08934v2 Announce Type: replace Abstract: Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components.

Nothing from Something: Can a Language Model Discover 0?

arXiv:2606. 17289v1 Announce Type: new Abstract: AI systems based on artificial neural networks are being developed with aspirations of pushing the boundary of human mathematical knowledge.

Explanations of Large Language Models Explain Language Representations in the Brain

arXiv:2502. 14671v4 Announce Type: replace-cross Abstract: Large Language Model (LLM) representations are known to align with brain activity during language processing, but it remains unclear what drives this alignment.

Beyond $L_2$: Generalizing Abductive Latent Explanations to Diverse Prototype-Based Architectures

arXiv:2608. 16773v1 Announce Type: new Abstract: Prototype-based neural networks are hailed as interpretable-by-design architectures.