© 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. 24064
    Prev
    Next
    INDEX
    Explanations

    index and positions

    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
    ecker
    -0.08
    .TryParse
    -0.07
    /ay
    -0.07
    ={<
    -0.07
    endu
    -0.07
    æŶæĹ¥
    -0.07
    æĢ¥äºĨ
    -0.07
     doty
    -0.07
    igg
    -0.07
    è¯ŃéŁ³æŶéķ¿
    -0.06
    POSITIVE LOGITS
     #__
    0.07
    ç®Ĺ
    0.07
    ä½įç½®
    0.07
    å¿ĥæĥ³äºĭæĪIJ
    0.06
     position
    0.06
     positions
    0.06
    adius
    0.06
    ä¸Ĭ涨äºĨ
    0.06
    Positions
    0.06
    æĻºèĥ½ç§ijæĬĢæľīéĻIJåħ¬åı¸
    0.06
    Activations Density 0.010%

    No Known Activations