# NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models

arXiv: https://arxiv.org/abs/2601.03671 · HTML: https://mlsanity.com/paper/2601.03671/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 8 of 8)

- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models](https://mlsanity.com/paper/2503.05613/) (2025)
- [Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models](https://mlsanity.com/paper/1808.00196/) (2018)
- [SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models](https://mlsanity.com/paper/2502.11356/) (2025)
- [KnowThyself: An Agentic Assistant for LLM Interpretability](https://mlsanity.com/paper/2511.03878/) (2025)

## Built on by (most cited first, 3 of 3)

- [How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings](https://mlsanity.com/paper/2606.00356/) (2026)
- [Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?](https://mlsanity.com/paper/2606.24026/) (2026)
- [MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations](https://mlsanity.com/paper/2610.02480/) (2026)

## Abstract (arXiv)

Neuron-level interpretation in large language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual neurons respond to multiple distinct semantic concepts. Existing single-pass interpretation methods struggle to faithfully capture such multi-concept behavior. In this work, we propose NeuronScope, a multi-agent framework that reformulates neuron interpretation as an iterative, activation-guided process. NeuronScope explicitly deconstructs neuron activations into atomic semantic components, clusters them into distinct semantic modes, and iteratively refines each explanation using neuron activation feedback. Experiments demonstrate that NeuronScope uncovers hidden polysemanticity and produces explanations with significantly higher activation correlation compared to single-pass baselines.