Qwen3.5-27B Gets Sparse Autoencoders: 81k Features Exposed

Qwen released Qwen-Scope, adding Sparse Autoencoders to Qwen3.5-27B, exposing 81k features across 64 layers for steerable inference. Qwen released Qwen-Scope, an interpretability toolkit adding Sparse Autoencoders to Qwen3.5-27B. The toolkit exposes...