© 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. 9928
    Prev
    Next
    INDEX
    Explanations

    is then duly, presenting, conceived, obtained, defined, listed, with, accordingly, to, processed

    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
    大水
    -0.08
    讲æ±Ĥ
    -0.08
    slag
    -0.07
    charg
    -0.07
    ardon
    -0.07
    ukur
    -0.07
    quis
    -0.07
    aign
    -0.07
    yb
    -0.07
    !!!!!
    -0.07
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥å®ĮåĸĦ
    0.07
    ä¸įæĸŃå®ĮåĸĦ
    0.07
     Dw
    0.07
    oleon
    0.07
    å¿ĥ头
    0.07
     narrative
    0.07
     refined
    0.07
    ç¥ŀçİĭ
    0.07
    saan
    0.06
    _dw
    0.06
    Activations Density 0.001%

    No Known Activations