© 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. 64636
    Prev
    Next
    INDEX
    Explanations

    names, diagram, radius, lineup, coordinates

    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
    ulet
    -0.10
    人åĿĩåı¯
    -0.08
    æľ¬ç«ĻåĨħ容
    -0.08
    itzt
    -0.08
    utorials
    -0.07
    ëĤŃ
    -0.07
    upert
    -0.07
    人åĿĩ
    -0.07
    翻天
    -0.07
    é¢ĺ为
    -0.07
    POSITIVE LOGITS
     eines
    0.10
     einer
    0.08
     ενÏĮÏĤ
    0.08
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.07
    ECO
    0.07
    สำหรัà¸ļ
    0.07
    对ä¸Ģ个
    0.07
     của
    0.07
    åĴĮçī¹çĤ¹
    0.07
    optgroup
    0.07
    Activations Density 0.521%

    No Known Activations