© 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. 59844
    Prev
    Next
    INDEX
    Explanations

    finite fields expandable by intervals

    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
    æīĢè°ĵ
    -0.08
    -0.07
     "
    -0.06
    大家éĥ½çŁ¥éģĵ
    -0.06
    è¯Ŀ说
    -0.06
     held
    -0.06
     *
    -0.06
    ä¹ĭéĹ´çļĦæĦŁæĥħ
    -0.06
     deliberately
    -0.06
     BSON
    -0.06
    POSITIVE LOGITS
    quiv
    0.09
     sehar
    0.08
     zaczy
    0.08
     almeno
    0.08
     Postar
    0.08
     Leban
    0.08
    <|box_end|>
    0.08
    ีà¹īยà¸ĩ
    0.08
     **:**
    0.08
    ordion
    0.08
    Activations Density 0.090%

    No Known Activations