© 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. 39228
    Prev
    Next
    INDEX
    Explanations

    date, finance, 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
    åĨĹ
    -0.08
    mero
    -0.08
    ÑģÑĤе
    -0.08
    æĮijçľī
    -0.07
    .neg
    -0.07
    filesize
    -0.07
     filesize
    -0.07
    åįĥåı¤
    -0.07
    约åįł
    -0.07
    meros
    -0.07
    POSITIVE LOGITS
    Forward
    0.08
     comp
    0.07
     Forward
    0.07
     Quarterly
    0.07
    weekly
    0.07
    温åĴĮ
    0.07
    TimeZone
    0.07
    åIJįä¹ī
    0.07
    åŃ£
    0.07
     monthly
    0.07
    Activations Density 0.002%

    No Known Activations