© 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. 15812
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponents

    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
    ç½®ä¹ĭ
    -0.09
    agus
    -0.08
    ä¼ļåIJĮ
    -0.08
    icolo
    -0.08
    HTTPRequest
    -0.08
    åħĪçĶ¨
    -0.07
    usses
    -0.07
    adore
    -0.07
    agÄĻ
    -0.07
    "${
    -0.07
    POSITIVE LOGITS
    éĥ¨åĪĨç»ĦæĪIJ
    0.06
     number
    0.06
    ä¸ĢäºĽå°ı
    0.06
    гон
    0.06
    azy
    0.06
    ynet
    0.06
    ytic
    0.06
    人æĦı
    0.06
    å°ijéĩıçļĦ
    0.06
     extra
    0.05
    Activations Density 0.036%

    No Known Activations