© 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. 47938
    Prev
    Next
    INDEX
    Explanations

    combinatorics and programming

    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
    s
    -0.09
    er
    -0.08
    ¸
    -0.07
    enburg
    -0.07
    ов
    -0.07
    nahme
    -0.07
    ibert
    -0.06
    en
    -0.06
    åľ¨å·¥ä½ľä¸Ĭ
    -0.06
    sak
    -0.06
    POSITIVE LOGITS
    sted
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    posix
    0.09
    à¤Łà¥Ģ
    0.09
    ystery
    0.08
    _DH
    0.08
    ethod
    0.08
    chenk
    0.08
    teh
    0.08
    achinery
    0.08
    Activations Density 0.001%

    No Known Activations