© 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. 8649
    Prev
    Next
    INDEX
    Explanations

    China, university, organisation, campus

    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
    ç»ĻåĪ«äºº
    -0.08
    大ä¼Ļ
    -0.07
    å°ıæ¡¥
    -0.07
    æľīçļĦ人
    -0.07
     Borders
    -0.07
    _instruction
    -0.07
    æ±ĩéĽĨ
    -0.07
    ä¸įåIJĮçļĦ人
    -0.07
    äºİäºĭ
    -0.07
    ãģ¾ãģĦ
    -0.07
    POSITIVE LOGITS
    åIJĪä½ľ
    0.08
    æ½ľåľ¨å®¢æĪ·
    0.08
    äºĨ解äºĨ
    0.08
     influential
    0.07
    æīĵ交éģĵ
    0.07
    /custom
    0.07
    æ½ľåľ¨
    0.07
    çļĦåIJĪä½ľ
    0.07
    éĢļè¿ĩä¸İ
    0.07
    .embed
    0.07
    Activations Density 0.498%

    No Known Activations