© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44680
    Prev
    Next
    INDEX
    Explanations

    on behalf of

    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
    Negative Logits
    èµĦä¿¡
    -0.07
    å¡ij
    -0.07
    ä¿ĿéĻ©èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    mic
    -0.06
    ruz
    -0.06
    ÑĪка
    -0.06
    nies
    -0.06
    мии
    -0.06
    åħ±åIJĮåıĤä¸İ
    -0.06
    athlon
    -0.06
    POSITIVE LOGITS
    ierce
    0.08
    ühle
    0.07
    æ»ķ
    0.07
    åįĹä¸ĭ
    0.07
    lán
    0.07
    eight
    0.07
    arei
    0.07
    yant
    0.07
    arder
    0.07
    iring
    0.07
    Activations Density 0.015%

    No Known Activations