© 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. 64787
    Prev
    Next
    INDEX
    Explanations

    Spock.li, JP, OR Meta, guest

    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
    anford
    -0.08
    ucci
    -0.07
    éĻĪå¿Ĺ
    -0.07
    åIJĪçIJĨè§ĦåĪĴ
    -0.07
    auge
    -0.06
     Swamp
    -0.06
     Toute
    -0.06
    ange
    -0.06
    å¿Ĺ强
    -0.06
    anu
    -0.06
    POSITIVE LOGITS
    æ¯Ķåݻ年åIJĮæľŁ
    0.07
    haal
    0.07
    биÑı
    0.07
    eltu
    0.07
    (dl
    0.07
    chl
    0.07
    LIO
    0.07
    roh
    0.07
    ogl
    0.07
    ollower
    0.06
    Activations Density 0.756%

    No Known Activations