© 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. 47132
    Prev
    Next
    INDEX
    Explanations

    "on-", "competition", "Point", "Demeter", "super", "riding", "problem", "Bird"

    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
    渴
    -0.06
    åѦæľīæīĢ
    -0.06
    è¡Įè¿Ľ
    -0.06
    //@
    -0.05
    æĭħ
    -0.05
    å¼ĢéĹ¨çº¢
    -0.05
    è´¢è¿IJ
    -0.05
    åIJĦçݯèĬĤ
    -0.05
    åı¯æĥ³èĢĮçŁ¥
    -0.05
    azit
    -0.05
    POSITIVE LOGITS
    大ä¸Ń
    0.08
    åıĪ称
    0.07
    ulich
    0.07
    queur
    0.07
    []=
    0.07
    豫
    0.07
    à¸Ľà¸²à¸Ļ
    0.07
    åıĪåı«
    0.07
    stwo
    0.07
    liest
    0.07
    Activations Density 0.489%

    No Known Activations