Research
impact 16
Mechanistic Interpretability of Antibody Language Models Using SAEs
Mechanistic Interpretability of Antibody Language Models Using SAEs arXiv:2512.05794v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used t…
Why it matters
For professionals tracking mechanistic, this is a data point worth bookmarking. The interpretability implications alone deserve follow-up.