© 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. 63653
    Prev
    Next
    INDEX
    Explanations

    acquiring, enable, find, record, forward, display, if, data, operator

    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
    ("--------------------------------
    -0.07
    leck
    -0.07
    )):
    -0.07
    以åıĬåľ¨
    -0.06
    åĴĮåľ¨
    -0.06
     sogenannten
    -0.06
     sogenannte
    -0.06
    ç§Ģ丽
    -0.06
    æĺķ
    -0.06
    /LICENSE
    -0.06
    POSITIVE LOGITS
     noqa
    0.10
    ä¸ĭåIJĮ
    0.09
     */,
    0.08
    åIJĮä¸Ĭ
    0.08
    dito
    0.08
    irting
    0.07
    dene
    0.07
    æĮº
    0.07
    纬
    0.07
    eraus
    0.07
    Activations Density 0.087%

    No Known Activations