© 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. 56740
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions (N x N)

    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
    <?>>
    -0.07
    Ñħа
    -0.07
    让è¿Ļ个
    -0.07
    åľ¨å¤ļ
    -0.07
    ('='
    -0.07
    ondere
    -0.07
    keley
    -0.07
    idium
    -0.07
    éĻ¤äºĨåľ¨
    -0.07
    è¿ĩ度çļĦ
    -0.07
    POSITIVE LOGITS
    大å°ı
    0.07
    åįĹåĮĹ
    0.07
    åħŃ大
    0.06
    rawd
    0.06
    PV
    0.06
    éĢļ常为
    0.06
    -svg
    0.06
     gá»ĵm
    0.06
    æ¡¥éķĩ
    0.06
    大å°ı为
    0.06
    Activations Density 0.036%

    No Known Activations