© 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. 31644
    Prev
    Next
    INDEX
    Explanations

    you're or your explain

    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
    èĢIJ
    -0.09
    avel
    -0.09
    azen
    -0.09
    å¤ĸç±į
    -0.08
    æĮ½
    -0.08
    åIJĦæĸ¹éĿ¢
    -0.08
    ä¸Ģåħ±
    -0.08
     бÑĥдÑĥÑĤ
    -0.08
    å°Ĩ继ç»Ń
    -0.08
    oad
    -0.08
    POSITIVE LOGITS
    .invalidate
    0.10
    èĥ½åĬĽå¼º
    0.09
    ä¸įåľ¨ä¹İ
    0.09
    ä½ķå¿ħ
    0.08
    å½ĵæĹ¥
    0.08
    tas
    0.08
    éļ¶å±ŀäºİ
    0.08
    à¹ģà¸ģ
    0.08
    ä¼ĺè´¨
    0.08
    å«Į
    0.08
    Activations Density 0.102%

    No Known Activations