© 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. 8228
    Prev
    Next
    INDEX
    Explanations

    {...} notation

    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
    vn
    -0.06
    #:
    -0.06
    oli
    -0.06
    ugi
    -0.06
    ><!--
    -0.06
    ))->
    -0.06
    environ
    -0.06
    zh
    -0.06
     excepc
    -0.06
    orem
    -0.06
    POSITIVE LOGITS
    ç¼Ī
    0.08
    nable
    0.08
    кеÑĢ
    0.07
     herself
    0.07
    лÑĮÑģкой
    0.07
    лÑĮÑģкого
    0.07
    /MPL
    0.07
    ä»ĭçŁ³
    0.07
    йÑĤеÑģÑĮ
    0.07
    elige
    0.07
    Activations Density 0.006%

    No Known Activations