Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

arXiv:2606.24026 · cs.AI · Submitted 2026-06-23 · Read on arXiv

cs.AI

Submitted: 2026-06-23

Updated: 2026-09-02

Code: https://github.com/Ziyu-Yao-NLP-Lab/LLM-Circuit-Explainer

Terminology

• Accuracy — 32× in this paper · explained in 1 episode
• Transformer — 24× in this paper · explained in 2 episodes
• Ablation — 19× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Interpretability — 19× in this paper · explained in 15 episodes
• LLM judge — 14× in this paper · explained in 2 episodes
• Mechanistic Interpretability — 12× in this paper
• Grounding — 10× in this paper · explained in 3 episodes
• Aggregation — 9× in this paper · explained in 1 episode
• Activation Patching — 5× in this paper · explained in 2 episodes
• Annotator Agreement — 5× in this paper · explained in 1 episode
• Pruning — 5× in this paper · explained in 4 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Decode — 3× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research
• Mechanistic Interpretability for AI Safety -- A Review
• A Primer on the Inner Workings of Transformer-based Language Models
• InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
• SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
• How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model
• Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
• Language Models Use Trigonometry to Do Addition
• A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
• Tracr: Compiled Transformers as a Laboratory for Interpretability
• NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
• TracrBench: Generating Interpretability Testbeds with Large Language Models
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
• Thinking Like Transformers
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
• Automated Interpretability and Feature Discovery in Language Models with Agents
• MIB: A Mechanistic Interpretability Benchmark
• LLM Evaluators Recognize and Favor Their Own Generations
• Automatically Interpreting Millions of Features in Large Language Models
• Qwen3 Technical Report

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection