© 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. 33665
    Prev
    Next
    INDEX
    Explanations

    true or false, referendum, card, reviews

    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
    usen
    -0.08
    usy
    -0.08
     Usai
    -0.08
    usin
    -0.08
    emean
    -0.08
    åĴĮé£İ
    -0.07
    reff
    -0.07
    rup
    -0.07
     exhaus
    -0.07
    =search
    -0.07
    POSITIVE LOGITS
    å¾Īé«ĺçļĦ
    0.08
    æł¡
    0.06
     Inst
    0.06
    ugar
    0.06
    _activ
    0.06
    oom
    0.06
    çħ§
    0.06
     comp
    0.06
    kannt
    0.06
     False
    0.06
    Activations Density 0.002%

    No Known Activations