© 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. 56634
    Prev
    Next
    INDEX
    Explanations

    code syntax separators

    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
    ÑģÑĤÑĢа
    -0.08
    åıijæĮ¥èĩªå·±çļĦ
    -0.07
    ething
    -0.07
     kara
    -0.07
    æĸ°è§Ħå®ļ
    -0.07
    estaan
    -0.06
    ä¸įå·®
    -0.06
    ä¸įåĢ¦
    -0.06
    town
    -0.06
    GOR
    -0.06
    POSITIVE LOGITS
    appartement
    0.07
    icoli
    0.07
    otec
    0.07
    zig
    0.06
    åŃIJåŃĻ
    0.06
    kis
    0.06
    åł
    0.06
    åŃIJæ§ĺ
    0.06
    OrCreate
    0.06
    èIJ¦ç»ķ
    0.06
    Activations Density 0.162%

    No Known Activations