© 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. 20267
    Prev
    Next
    INDEX
    Explanations

    regions, periods, sectors, formats, gender

    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
    poster
    -0.09
    åıĬåħ¶
    -0.08
    è¿ŀåIJĮ
    -0.07
    è¯ĬæĸŃåıĬ
    -0.07
    ö
    -0.06
    htm
    -0.06
    è°ĥæķ´åĴĮ
    -0.06
    ä¸ĢäºĽ
    -0.06
    ombe
    -0.06
    TION
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.09
     hinweg
    0.08
    ä¸įåIJĮçļĦ人
    0.08
     genders
    0.08
    满足ä¸įåIJĮ
    0.07
    urb
    0.07
    ä¸įåIJĮç±»åŀĭçļĦ
    0.07
     different
    0.07
    subtype
    0.07
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.07
    Activations Density 0.218%

    No Known Activations