© 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. 41952
    Prev
    Next
    INDEX
    Explanations

    names of people, often followed by titles or locations

    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
    诸ä½į
    -0.07
    æĻļè¾Ī
    -0.07
    åIJĮä»ģ
    -0.07
     subordinate
    -0.07
    æļĹ示
    -0.07
    æĦļèł¢
    -0.06
    èĻļ伪
    -0.06
    éĿĴ年人
    -0.06
     whichever
    -0.06
    æµģ产
    -0.06
    POSITIVE LOGITS
    åĮĸåIJį
    0.10
    åľ¨å½ĵåľ°
    0.09
    åijĬè¯īè®°èĢħ
    0.09
     ÙĬبÙĦغ
    0.08
    åIJįåı«
    0.08
    ç£
    0.08
    ccion
    0.08
     плоÑīадÑĮÑİ
    0.08
     à¸Ńายุ
    0.07
    ä¸İå½ĵåľ°
    0.07
    Activations Density 1.360%

    No Known Activations