© 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. 18907
    Prev
    Next
    INDEX
    Explanations

    id sequences

    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
    èµ·æĭį
    -0.07
    彤
    -0.07
    ->_
    -0.07
    æŶæ¯ı
    -0.06
     prescind
    -0.06
    arau
    -0.06
    çĽ¸çº¦
    -0.06
    Svg
    -0.06
    imized
    -0.06
    é¦Ĩ
    -0.06
    POSITIVE LOGITS
    ipy
    0.08
    osal
    0.08
     Geh
    0.07
     *.*
    0.07
    éĢļ常æĥħåĨµä¸ĭ
    0.07
    FAULT
    0.07
    è®°èĢħ
    0.07
     Inox
    0.07
    è¡ħ
    0.07
    agna
    0.06
    Activations Density 0.003%

    No Known Activations