© 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. 55943
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

    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
    undi
    -0.08
    ä¸ĢæĪ·
    -0.08
    spre
    -0.07
     á»ķ
    -0.07
    storm
    -0.07
    大éĢī
    -0.06
    ä¸įåı¯æĢķ
    -0.06
    veau
    -0.06
    oghi
    -0.06
    è¶Ĭè¿ĩ
    -0.06
    POSITIVE LOGITS
    å¤ĸå½¢
    0.07
     magnitude
    0.07
    åIJĬ
    0.07
    æĪIJ
    0.07
    ç»ıèIJ¥é¡¹çĽ®
    0.07
    imei
    0.07
    زارÛĮ
    0.07
     Meine
    0.06
    ley
    0.06
    urier
    0.06
    Activations Density 0.001%

    No Known Activations