© 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. 49283
    Prev
    Next
    INDEX
    Explanations

    č followed by markup

    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
    大å¸Ĥåľº
    -0.08
    éĻ¤æģ¶
    -0.07
    ç²¾åĵģ课ç¨ĭ
    -0.07
    [property
    -0.06
    uskan
    -0.06
     Bedford
    -0.06
    ä¸ĸçķĮä¸ĬæľĢ
    -0.06
    åľ¨åĪ«äºº
    -0.06
    æĹ¢çĦ¶
    -0.06
    æĪij们è¿Ļ个
    -0.06
    POSITIVE LOGITS
    lyph
    0.08
    éħį
    0.08
    สัà¸Ļ
    0.07
    ëªħíķľ
    0.07
    æĺ¯ç¬¬ä¸Ģ
    0.07
    è¹ĭ
    0.07
    opard
    0.07
    éĢ
    0.06
    иÑģÑĤо
    0.06
    éĿłå·¦
    0.06
    Activations Density 0.325%

    No Known Activations