SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations

ArXi:2510.02734v2 Announce Type: replace-cross Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA language models such as RiNALMo. Recent work has begun applying sparse autoencoders (SAEs) to protein language model representations, exploring representation-level interpretability in biomolecular models.