© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    file extensions or comments

    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
    zás
    -0.07
    atta
    -0.07
    海鸥
    -0.07
    hort
    -0.07
    riles
    -0.07
    å°ĶèĴĻ
    -0.06
    olis
    -0.06
    adients
    -0.06
    aldi
    -0.06
    annotations
    -0.06
    POSITIVE LOGITS
    Å¡n
    0.07
    æŃ£ç¡®å¤ĦçIJĨ
    0.06
    à¸Ļà¸Ļ
    0.06
    ding
    0.06
    BUF
    0.06
    æĺŁçģ«
    0.06
    æŃ£éģĵ
    0.06
    yo
    0.06
     Lap
    0.06
    usto
    0.06
    Activations Density 0.302%

    No Known Activations