© 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. 65276
    Prev
    Next
    INDEX
    Explanations

    no direct experience, but

    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
    ä¸įæıIJ
    -0.08
    erve
    -0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
    zung
    -0.07
    ä¸įä¼ļåĨį
    -0.07
    ç»ıæµİå½¢åĬ¿
    -0.07
    带æĿ¥æĽ´å¤ļ
    -0.07
    attore
    -0.07
    è¿ĺä¼ļåĩºçİ°
    -0.07
    ÙĪÛĮÙĦ
    -0.07
    POSITIVE LOGITS
    hift
    0.08
    gaard
    0.08
    æĩ¿
    0.07
    裾
    0.07
    idak
    0.07
    apons
    0.07
    gues
    0.07
    å·§
    0.07
    æĸ°çŁ¥è¯Ĩ
    0.07
     rely
    0.06
    Activations Density 0.010%

    No Known Activations