© 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. 38471
    Prev
    Next
    INDEX
    Explanations

    question marks and statements

    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
    loff
    -0.08
    Ỽt
    -0.07
    ãģķãģĦ
    -0.07
    ekin
    -0.07
    uze
    -0.07
    åĪĿ
    -0.07
     بعضÙĩا
    -0.07
    ë¡Ŀ
    -0.06
    èİŀ
    -0.06
    bage
    -0.06
    POSITIVE LOGITS
    èĭ±æĸĩåIJį
    0.08
    arte
    0.07
     catena
    0.07
    æŀĦæŀ¶
    0.07
     chain
    0.07
     gem
    0.07
    èĭ±æĸĩåIJį称
    0.07
    è¿Ļ个åIJįåŃĹ
    0.07
    ä¼ģä¸ļåIJį称
    0.07
    æĸĩåѦç½ij
    0.07
    Activations Density 0.001%

    No Known Activations