© 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. 39264
    Prev
    Next
    INDEX
    Explanations

    run or serve commands

    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
    occhi
    -0.08
    .Globalization
    -0.07
    /rfc
    -0.07
    _BEGIN
    -0.07
    éķľå¤´éĩĮ
    -0.07
     Wilkinson
    -0.07
    æ±Łå¤ı
    -0.07
    顺åĬ¿
    -0.07
    apol
    -0.06
    顺
    -0.06
    POSITIVE LOGITS
     runnable
    0.11
    è¿IJè¡Į
    0.09
    .run
    0.09
    -run
    0.09
    è¿IJè¡ĮçļĦ
    0.09
     thá»Ń
    0.09
    /run
    0.08
     running
    0.08
     runs
    0.08
    /debug
    0.08
    Activations Density 0.710%

    No Known Activations