© 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. 10765
    Prev
    Next
    INDEX
    Explanations

    conversion and mapping

    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
    ayat
    -0.07
    elang
    -0.07
    .controllers
    -0.07
    ุà¸Ķ
    -0.07
     imp
    -0.07
    ayani
    -0.07
    itari
    -0.07
    åħ«å¤§
    -0.07
    æĿĢæīĭ
    -0.07
     onKeyDown
    -0.07
    POSITIVE LOGITS
    转æį¢
    0.16
     conversion
    0.15
     converting
    0.13
    conversion
    0.13
     conversions
    0.13
     converts
    0.12
     converters
    0.12
    转æį¢åĻ¨
    0.12
     Conversion
    0.12
    convert
    0.12
    Activations Density 0.196%

    No Known Activations