© 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. 18403
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numbers

    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
    _generated
    -0.07
    jab
    -0.06
    пок
    -0.06
    ucer
    -0.06
    ulti
    -0.06
    oref
    -0.06
     ['.
    -0.06
    eret
    -0.06
    ä¸į好çļĦ
    -0.06
    æ§
    -0.06
    POSITIVE LOGITS
    elsea
    0.08
    åĮ»éĻ¢åľ°åĿĢ
    0.07
    xfff
    0.07
    å¼ģ
    0.07
    ĽĦ
    0.07
     Soh
    0.07
    resenter
    0.07
    好æŃ¹
    0.07
    ushi
    0.07
    aix
    0.07
    Activations Density 0.003%

    No Known Activations