© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30027
    Prev
    Next
    INDEX
    Explanations

    data and information

    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
    åIJĦ个æĸ¹éĿ¢
    -0.08
    ä¸Ģ个好çļĦ
    -0.08
    模åŀĭçļĦ
    -0.08
    attore
    -0.08
     originals
    -0.08
    æݪæĸ½çļĦ
    -0.08
    antages
    -0.07
    è¿Ļæł·çļĦä¸Ģ个
    -0.07
    ç»ĵæŀľçļĦ
    -0.07
    æijĩæijĩ
    -0.07
    POSITIVE LOGITS
     footage
    0.09
    æķ°æį®è¿Ľè¡Į
    0.08
     accumulated
    0.08
     data
    0.08
     information
    0.08
    æĿ¥èĩª
    0.07
    æĿ¥èĩªäºİ
    0.07
     calories
    0.07
    è¯ĿæĿ¥
    0.07
     additional
    0.07
    Activations Density 0.956%

    No Known Activations