© 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. 55301
    Prev
    Next
    INDEX
    Explanations

    .util or .utils

    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
    .debian
    -0.07
    arang
    -0.07
     Sporting
    -0.07
    agul
    -0.07
    å¡ĺéķĩ
    -0.06
    èīºæľ¯åĽ¢
    -0.06
    uada
    -0.06
     dÃłi
    -0.06
    ä¸ĢçĶŁä¸Ń
    -0.06
     "---
    -0.06
    POSITIVE LOGITS
    .util
    0.08
    _utils
    0.08
    util
    0.08
    utils
    0.08
     util
    0.08
    immy
    0.07
    ::
    0.07
     utils
    0.07
    .utils
    0.07
    çĴ¨
    0.07
    Activations Density 0.702%

    No Known Activations