© 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. 16455
    Prev
    Next
    INDEX
    Explanations

    medical intervention, therapy, economic, risk

    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
    è¯ģæį®è¯ģæĺİ
    -0.09
    并ç»ĵåIJĪ
    -0.08
    oose
    -0.07
    OwnProperty
    -0.07
    é¢ľèī²åĴĮ
    -0.07
    ä¼Łå¤§å¤įåħ´
    -0.07
    OOSE
    -0.07
    èĥĮæĻ¯åĴĮ
    -0.07
    haber
    -0.07
    insen
    -0.07
    POSITIVE LOGITS
    ç¿
    0.08
    (getContext
    0.08
    irection
    0.07
    -worthy
    0.07
    plo
    0.07
     bý
    0.07
    pace
    0.07
    åı¯æľŁ
    0.06
    æĿ¥èĩªäºİ
    0.06
    ä¸įçĶ±èĩªä¸»
    0.06
    Activations Density 0.025%

    No Known Activations