© 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. 41056
    Prev
    Next
    INDEX
    Explanations

    end of sentence or list item

    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
    ìŀ¥
    -0.08
    oppers
    -0.07
    ä¸įåı¯
    -0.07
    æ³ī
    -0.07
    glob
    -0.07
    pheres
    -0.07
    ouz
    -0.07
    çİ°å½¹
    -0.07
    _marshall
    -0.06
     replacements
    -0.06
    POSITIVE LOGITS
    足
    0.07
    ä¸Ģåıį
    0.07
    ÙĬرÙĬ
    0.07
    æ¯ıä¸Ģç§į
    0.06
    èĥ½å¤Łå¿«éĢŁ
    0.06
    upo
    0.06
    XC
    0.06
    èĵ
    0.06
    æĺ¥ç§ĭ
    0.06
    豫
    0.06
    Activations Density 0.112%

    No Known Activations