© 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. 65477
    Prev
    Next
    INDEX
    Explanations

    different types and categories

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ãģ»ãģĨ
    -0.07
    åħ¨éĥ¨åĨħ容
    -0.07
     же
    -0.07
     ÙĥÙĦÙĩ
    -0.07
     berupa
    -0.07
    à®ŀ
    -0.07
     Medina
    -0.07
     newest
    -0.07
    çļĦä»»ä½ķ
    -0.06
    POSITIVE LOGITS
    æľīä¸įåIJĮçļĦ
    0.21
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.17
    åľ¨ä¸įåIJĮçļĦ
    0.17
    ä¸įåIJĮçļĦ
    0.17
    æĺ¯ä¸įåIJĮçļĦ
    0.15
    æľīä¸įåIJĮ
    0.15
    ä¸įåIJĮçļĦ人
    0.15
     different
    0.14
    éĥ½æľīä¸įåIJĮçļĦ
    0.14
    different
    0.14
    Activations Density 0.291%

    No Known Activations