© 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. 19717
    Prev
    Next
    INDEX
    Explanations

    hexadecimal notations

    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
    èĮī
    -0.09
    ron
    -0.08
    ness
    -0.08
    erness
    -0.08
    ers
    -0.08
    ble
    -0.08
    ibility
    -0.08
    cel
    -0.07
    gang
    -0.07
    sey
    -0.07
    POSITIVE LOGITS
    isson
    0.08
    lems
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    çļĦ
    0.07
    égor
    0.07
    osition
    0.07
    IELDS
    0.07
    æľīåIJįãģª
    0.07
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.06
    apiers
    0.06
    Activations Density 0.015%

    No Known Activations