© 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. 11713
    Prev
    Next
    INDEX
    Explanations

    estate

    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
     Elas
    -0.07
    èĭijå°ıåĮº
    -0.07
    owell
    -0.07
    rast
    -0.07
    ...",
    -0.07
    姻
    -0.06
    åĪ¤åĨ³å¦Ĥä¸ĭ
    -0.06
    rst
    -0.06
    æIJº
    -0.06
    ç«ĭ马
    -0.06
    POSITIVE LOGITS
    ãģĵãģ¡ãĤīãĤĤ
    0.13
    ãģĵãģ¡ãĤīãģ¯
    0.11
     ebenfalls
    0.11
    ãģĵãĤĮãĤĤ
    0.09
    åIJĮæł·
    0.08
    Again
    0.08
     again
    0.08
     Again
    0.08
     likewise
    0.08
     szint
    0.07
    Activations Density 0.095%

    No Known Activations