© 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. 50418
    Prev
    Next
    INDEX
    Explanations

    calendar, persian, .orig

    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
    alf
    -0.08
    oub
    -0.07
    æĸ°é²ľçļĦ
    -0.07
    载人
    -0.07
    зон
    -0.06
    sab
    -0.06
    为ä¹ĭ
    -0.06
    icken
    -0.06
    æĸ°é²ľ
    -0.06
    大è¯Ŀ
    -0.06
    POSITIVE LOGITS
    clang
    0.08
    éľ
    0.08
    空éĹ´çļĦ
    0.07
    çŁ¢
    0.07
    å°º
    0.07
    виÑĤ
    0.07
    enske
    0.07
    æľīæĿ¡ä¸įç´Ĭ
    0.07
    arent
    0.07
    æľīåºıå¼Ģå±ķ
    0.07
    Activations Density 0.002%

    No Known Activations