Mechanistic Interpretability

• Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

  Jun 25, 2026

  A mechanistic interpretability study showing how security fine-tuning can specialize inherited model circuits into brittle indicator rules while preserving standard benchmark accuracy.

• Applied Interpretability: Foundation-Sec-Instruct Goes Under the Microscope

  Feb 26, 2026

  Exploring mechanistic interpretability methods for understanding internal behavior of security-focused language models.