© 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. 21956
    Prev
    Next
    INDEX
    Explanations

    behind, attempts, extra, the

    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
    akai
    -0.08
    æıIJåIJį
    -0.08
    ingk
    -0.07
    ardt
    -0.07
    zit
    -0.07
    èĢĮå¾ĹåIJį
    -0.07
    inge
    -0.07
    ingo
    -0.07
    lope
    -0.06
    orton
    -0.06
    POSITIVE LOGITS
    é¢ĦæĸĻ
    0.08
    ä¸Ģç§Ĵ
    0.08
    æĹ·
    0.07
     debug
    0.07
    raud
    0.07
    åħħåĪĨè°ĥåĬ¨
    0.07
    é¢ĦæľŁ
    0.07
     foresee
    0.07
     Desktop
    0.07
     default
    0.07
    Activations Density 0.014%

    No Known Activations