© 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. 21061
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or latex commands

    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
    ä¸įåıij
    -0.08
    aur
    -0.07
    pe
    -0.07
    ipro
    -0.07
    oley
    -0.06
     ski
    -0.06
     whip
    -0.06
    ä½ĻçĶŁ
    -0.06
     surf
    -0.06
    åı¯éĿłçļĦ
    -0.06
    POSITIVE LOGITS
    ignan
    0.07
    ohana
    0.07
    udu
    0.07
    ç©¿è¡Į
    0.07
    ÃģP
    0.07
    iance
    0.07
    Sense
    0.06
    Scaler
    0.06
    æ¹
    0.06
    åĽŀæĿ¥
    0.06
    Activations Density 0.001%

    No Known Activations