© 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. 28207
    Prev
    Next
    INDEX
    Explanations

    programming keywords: page, range, logger, profile, mail, log, date, assert, session

    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
    bacher
    -0.08
    ourage
    -0.08
    OrUpdate
    -0.07
    /licenses
    -0.07
    etre
    -0.07
    Ñĺи
    -0.07
    .JsonIgnore
    -0.07
    ãĤĦãģķ
    -0.07
    °
    -0.07
    anke
    -0.07
    POSITIVE LOGITS
    iram
    0.07
    ثة
    0.06
    .gov
    0.06
    .Lookup
    0.06
    æĴĴ
    0.06
    ä¸ĥåįģäºĮ
    0.06
    åĴĮæľ¬
    0.06
    unte
    0.06
    zell
    0.06
    ụng
    0.05
    Activations Density 0.393%

    No Known Activations