© 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. 47763
    Prev
    Next
    INDEX
    Explanations

    layer or layers

    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¸Ģ个个
    -0.08
     Lump
    -0.07
    izio
    -0.07
    à¸Ĺัà¹Īว
    -0.07
    æĶ¯éĥ¨
    -0.07
    年度æĬ¥åijĬ
    -0.07
    ä¸įèĥ½è¯´
    -0.07
    à°·à±į
    -0.07
    acman
    -0.06
    æ¡Ī件ä¸Ń
    -0.06
    POSITIVE LOGITS
     layer
    0.18
     layers
    0.18
    两å±Ĥ
    0.17
    å±Ĥ
    0.17
    層
    0.17
    ä¸Ģå±Ĥ
    0.15
    layer
    0.15
    å±ĤçļĦ
    0.15
    -layer
    0.15
    layers
    0.15
    Activations Density 0.174%

    No Known Activations