© 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. 45549
    Prev
    Next
    INDEX
    Explanations

    beginning of document sections

    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
    课åīį
    -0.07
    umo
    -0.07
    кÑĢа
    -0.07
    æł¼æĸ¯
    -0.07
    éĤ£æĺ¯æĪij
    -0.07
    idis
    -0.06
     herk
    -0.06
    å¾Ĺåĥı
    -0.06
     corner
    -0.06
    éĤ£æł·çļĦ
    -0.06
    POSITIVE LOGITS
     Autore
    0.08
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    atement
    0.08
    æ³ķæĺ¯
    0.08
    人被
    0.07
    ³
    0.07
    éĩįæĿ¥
    0.07
    åĽ´ç»ķçĿĢ
    0.07
    _detach
    0.07
    ç½ijç«Ļåľ°åĽ¾
    0.07
    Activations Density 0.495%

    No Known Activations