© 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. 34384
    Prev
    Next
    INDEX
    Explanations

    percentile curves or rankings

    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
    ê°Ģ
    -0.10
    voud
    -0.09
    ÛĮات
    -0.08
    esis
    -0.08
    itecture
    -0.08
    ignment
    -0.08
    ·
    -0.08
    तà¥įम
    -0.08
    ç»´åIJ¾å°Ķèĩªæ²»åĮº
    -0.08
    thetic
    -0.07
    POSITIVE LOGITS
    ting
    0.12
    ational
    0.10
    ally
    0.09
    iously
    0.08
    ician
    0.08
    rary
    0.08
    人æĿ¥è¯´
    0.08
     tÄĥm
    0.08
    и
    0.08
    خاذ
    0.08
    Activations Density 0.003%

    No Known Activations