© 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. 11368
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    pan
    -0.08
    åĴĮè¦ģæ±Ĥ
    -0.08
    åªĴ
    -0.07
    ouser
    -0.07
    段æŶéĹ´
    -0.07
    åĴĮ建议
    -0.07
    adr
    -0.06
    èĭ±éĩĮ
    -0.06
    uban
    -0.06
    eloos
    -0.06
    POSITIVE LOGITS
    _utils
    0.09
    é¢ĨåŁŁä¸Ń
    0.08
    åѦä¸Ń
    0.08
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    0.08
    inds
    0.08
    åı²ä¸ĬçļĦ
    0.08
     basics
    0.07
     theory
    0.07
    åı²ä¸Ĭ
    0.07
    æĸ¹éĿ¢çļĦ
    0.07
    Activations Density 0.495%

    No Known Activations