© 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. 45524
    Prev
    Next
    INDEX
    Explanations

    a type of

    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
    lement
    -0.08
    bauer
    -0.08
    elter
    -0.08
    çijŁ
    -0.07
    åĴĸåĸ±
    -0.07
    keypress
    -0.07
    uÅŁ
    -0.07
    ãĤ¢ãĥĹãĥŃãĥ¼ãĥģ
    -0.07
     ctor
    -0.07
    igt
    -0.07
    POSITIVE LOGITS
    ç®ĢåįķæĿ¥è¯´
    0.08
    ä¸Ģç§į
    0.07
    çļĦä¸Ģç§į
    0.07
    å¾ĹåIJį
    0.07
    ots
    0.07
    éŁ¿
    0.07
    ä¸ĵéŨ
    0.07
     czyli
    0.07
    ä¹Łåı«
    0.06
    æĦı为
    0.06
    Activations Density 0.255%

    No Known Activations