© 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. 31952
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    éģĵ
    -0.07
    .download
    -0.07
     viz
    -0.07
    />\
    -0.07
    _sv
    -0.07
    TRIES
    -0.07
    woff
    -0.07
    é¢Ĩä¼ļ
    -0.07
    brace
    -0.07
    æĸĩåįļ
    -0.07
    POSITIVE LOGITS
    æīį对
    0.09
    æĺµ
    0.09
     Daun
    0.08
    ragments
    0.07
    æĪijåij¢
    0.07
    mdir
    0.07
    ä½łåij¢
    0.07
    mong
    0.07
    inger
    0.06
    æľīå¥ĸ
    0.06
    Activations Density 0.009%

    No Known Activations