© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    function main() arguments

    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
     “[
    -0.08
    écie
    -0.08
    YTE
    -0.08
    åĩºèµĦé¢Ŀ
    -0.08
    éļ¾æ±Ĥ
    -0.08
    .cv
    -0.07
    %C
    -0.07
    >Hello
    -0.07
    arty
    -0.07
    缸éļı
    -0.07
    POSITIVE LOGITS
    æĨ¬
    0.06
    inus
    0.06
     etree
    0.06
    èŃ¦å¯Ł
    0.06
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.06
    ÖĦ
    0.06
    bull
    0.06
    _completion
    0.06
    resentation
    0.06
    ach
    0.06
    Activations Density 0.003%

    No Known Activations