© 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. 1061
    Prev
    Next
    INDEX
    Explanations

    waiting for something

    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
     künftig
    -0.08
    çŃī级çļĦ
    -0.08
    upgrade
    -0.07
    ärke
    -0.07
    èĩªåı¤
    -0.07
    ä»Ĭå¾Į
    -0.07
    èĩªåı¤ä»¥æĿ¥
    -0.07
    ABIL
    -0.07
    çŃī级
    -0.07
    ä»ĬåIJİ
    -0.07
    POSITIVE LOGITS
     ÑĥÑģп
    0.15
    æĿ¥ä¸įåıĬ
    0.15
     ÑĥÑģпе
    0.14
    æĿ¥å¾ĹåıĬ
    0.13
    累积
    0.11
    éĶĻè¿ĩäºĨ
    0.10
    è¿ĺ没æĿ¥å¾ĹåıĬ
    0.10
    à¸Ĺัà¸Ļ
    0.09
    åľ¨è¿Ļ段æŶéĹ´
    0.09
    éĶĻè¿ĩ
    0.09
    Activations Density 0.182%

    No Known Activations