© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46577
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and text formatting

    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
    ande
    -0.06
     Zip
    -0.06
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.06
    Pad
    -0.06
    æľĢæĸ°èµĦ讯
    -0.06
    ffc
    -0.06
    è¯Ĺæĥħ
    -0.06
    人æĦı
    -0.06
     aug
    -0.06
     Pad
    -0.06
    POSITIVE LOGITS
    ights
    0.09
    ewater
    0.08
    lopen
    0.08
    amedi
    0.07
    _kw
    0.07
    èĢ¿
    0.07
    åĪĨåĪ«
    0.07
     ÙħÙĤت
    0.07
    رÙĪÙģ
    0.07
    çļĦåħ±åIJĮ
    0.07
    Activations Density 0.004%

    No Known Activations