© 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. 65140
    Prev
    Next
    INDEX
    Explanations

    have + article or common word

    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
    quÃŃ
    -0.08
    ed
    -0.08
    ä¸įåIJĮç±»åŀĭ
    -0.08
    .twig
    -0.08
    aÅŁ
    -0.08
     ìĿ¸íķ´
    -0.08
    different
    -0.08
    ä¸įåIJĮçļĦ
    -0.07
    åIJĦç§įåİŁåĽł
    -0.07
    republik
    -0.07
    POSITIVE LOGITS
    çĿĢä¸Ģé¢Ĺ
    0.07
    çĿĢä¸Ģ
    0.07
    ª
    0.07
    ãģ¨ãģĵãĤį
    0.07
    ä½łåģļ
    0.07
    çī¹åĭĴ
    0.07
    vid
    0.07
    åĪ°å¤§
    0.06
    irectory
    0.06
    ational
    0.06
    Activations Density 0.083%

    No Known Activations