Final ordered-features model after generate-K GRPO RL (AV + co-trained critic).

Part of the NLA ordered-features (nested-dropout RL) PoC: an Activation Verbalizer trained so its ~10 next-token-prediction features are ordered most->least important, via random feature-prefix truncation (nested dropout) during GRPO RL. Code: feat/nla-ordered-features-rl on https://github.com/syvb/nanoNLA . Base model: Qwen/Qwen3-8B, layer 24.

Collection: https://huggingface.co/collections/syvb/nla-ordered-features-nested-dropout-rl-6a389fb18e68d281891e4061