© 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. 42769
    Prev
    Next
    INDEX
    Explanations

    each, variations, quantity

    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
    ibel
    -0.07
    ç»ĵ
    -0.07
    èĢĮå¤į
    -0.07
    .return
    -0.07
     ná»iji
    -0.07
    oft
    -0.07
    ếc
    -0.07
    atern
    -0.07
    ä¸ĩæĸ¹
    -0.07
    à¹Īà¸ĩ
    -0.07
    POSITIVE LOGITS
    åij¼åij¼
    0.07
    ä¸Ńèĭ±æĸĩ
    0.06
     corresponds
    0.06
     Panthers
    0.06
    ç§įç±»çļĦ
    0.06
     Correspond
    0.06
    å¾Ĺä¸Ĭ
    0.06
    etus
    0.06
    ç±»åŀĭçļĦ
    0.06
     abras
    0.06
    Activations Density 0.015%

    No Known Activations