© 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. 38562
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    é£İéĽª
    -0.08
    åĸ§åĵĹ
    -0.07
    urator
    -0.07
    olan
    -0.07
    ndon
    -0.07
    ainers
    -0.06
    .nodeType
    -0.06
     SESSION
    -0.06
    ä¹°çĤ¹
    -0.06
    ibrary
    -0.06
    POSITIVE LOGITS
    acol
    0.07
    zio
    0.07
    åĪ»
    0.07
    DirectoryName
    0.07
     reminis
    0.07
    ché
    0.07
    ×¢×Ļ
    0.07
     elog
    0.07
    ÑĮÑı
    0.07
    ÑĨеÑĢ
    0.07
    Activations Density 0.003%

    No Known Activations