© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41730
    Prev
    Next
    INDEX
    Explanations

    group theory elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folgen
    -0.07
    ä¸įåĢĴ
    -0.07
    stop
    -0.07
    ä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    -0.07
     cushions
    -0.07
    oton
    -0.07
     Seri
    -0.07
     ident
    -0.06
    attan
    -0.06
    建设ä¸İ
    -0.06
    POSITIVE LOGITS
    Outside
    0.08
     outside
    0.08
     Outside
    0.08
    è¿ĽæĿ¥
    0.08
    è§ĤéŁ³
    0.07
    åľ¨å¤ĸ
    0.07
    outside
    0.07
    éĢ²ä¾Ĩ
    0.07
    ä¸įå½Ĵ
    0.07
    å¤ĸéĿ¢
    0.07
    Activations Density 0.009%

    No Known Activations