© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4527
    Prev
    Next
    INDEX
    Explanations

    -ending injury, -threatening severe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ个æĸ°çļĦ
    -0.09
     jakiÅĽ
    -0.09
    ç¿ħ
    -0.09
    å¿ĥ缮ä¸Ń
    -0.08
    assen
    -0.08
    ç²¾ç¥ŀ
    -0.08
    åĩ°
    -0.08
    iqué
    -0.08
    宿
    -0.08
    ÇĶ
    -0.08
    POSITIVE LOGITS
    æĬķèŀįèµĦ
    0.10
    å¥ł
    0.08
    è°İ
    0.08
    缴èĩ³
    0.08
     Wong
    0.08
    çļĦä¸ľè¥¿
    0.08
    åij¤
    0.08
    ãģıãĤĮ
    0.08
    飬
    0.08
    没äºĨ
    0.08
    Activations Density 0.161%

    No Known Activations