© 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. 9770
    Prev
    Next
    INDEX
    Explanations

    date, number

    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
    opter
    -0.07
    pec
    -0.07
    edale
    -0.07
    eck
    -0.07
    afort
    -0.07
    çļĦåīįæĻ¯
    -0.07
    arze
    -0.07
    ¢
    -0.07
     Leist
    -0.07
     Juárez
    -0.07
    POSITIVE LOGITS
    _each
    0.07
    æ£ł
    0.07
     hus
    0.06
    nk
    0.06
    úr
    0.06
    udo
    0.06
    udden
    0.06
     ajar
    0.06
    ä¸Ĭ级
    0.06
    è¿Ł
    0.06
    Activations Density 0.010%

    No Known Activations