© 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. 35264
    Prev
    Next
    INDEX
    Explanations

    homeocysteine

    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
     whe
    -0.11
    西åįĹ
    -0.09
     Whe
    -0.09
    ÑĥÑĩ
    -0.09
    lag
    -0.09
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
     Micha
    -0.08
     Highlander
    -0.08
    æ¾ľ
    -0.08
    uali
    -0.08
    POSITIVE LOGITS
    ç«¥è¯Ŀ
    0.09
    ä¸ĭæīĭ
    0.09
    åĺ´éĩĮ
    0.09
    建ç«ĭåģ¥åħ¨
    0.09
    彩èĻ¹
    0.08
    (Cs
    0.08
    çľ¼ç¥ŀ
    0.08
    /plugin
    0.08
    enson
    0.08
     CS
    0.08
    Activations Density 0.043%

    No Known Activations