ACE: New Interpretability Method Extracts Shared Circuits Across LLM Trainings Up to 32B

CatAstro_Piyush · x · 2026-11-19

A new interpretability method called ACE, appearing at NeurIPS 2026, tackles a fundamental puzzle: train the same AI three times and you get identical behavior but different circuits — so is a circuit the algorithm, or just one implementation of it?

Original post →

More from Research

Research channel →