© 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. 41321
    Prev
    Next
    INDEX
    Explanations

    bold markdown formatting

    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
    ÙĨÙģ
    -0.07
    oeff
    -0.07
    临
    -0.07
    imbul
    -0.06
    ç´§
    -0.06
    ittance
    -0.06
    ÑģÑĤÑı
    -0.06
    æĤ¨çļĦè¯Ħ论
    -0.06
    贵人
    -0.06
    istas
    -0.06
    POSITIVE LOGITS
    rael
    0.07
    ายà¸Ļ
    0.07
    ä¿ĿæĮģèī¯å¥½çļĦ
    0.07
    è¿ijäºĽ
    0.07
    amentals
    0.07
    çIJ³
    0.07
    缸åħ³æݨèįIJ
    0.07
    verture
    0.07
    ancies
    0.07
    åľ¨æľĢè¿ij
    0.06
    Activations Density 0.009%

    No Known Activations