© 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. 65474
    Prev
    Next
    INDEX
    Explanations

    html body tags

    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
    IDA
    -0.07
    .readyState
    -0.07
    æµģçļĦ
    -0.07
    _probe
    -0.07
    ç¢Ł
    -0.07
    èĥŃ
    -0.07
    IQ
    -0.07
    ICAS
    -0.07
    æ´ĭ
    -0.07
    æij
    -0.07
    POSITIVE LOGITS
    æĺ¯æķ´ä¸ª
    0.08
    /global
    0.08
    åħ¨å±Ģ
    0.08
    对æķ´ä¸ª
    0.07
     ìłĦì²´
    0.07
    utar
    0.07
    åħ¨ä½ĵãģ®
    0.07
    è¿Ļ个大
    0.07
    gur
    0.07
    -wide
    0.07
    Activations Density 0.193%

    No Known Activations