© 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. 2019
    Prev
    Next
    INDEX
    Explanations

    CoA compounds

    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
     rét
    -0.07
    il
    -0.07
     strengths
    -0.06
    Õ«ÖĢ
    -0.06
    éĿ¢æĿ¡
    -0.06
     interp
    -0.06
    é©¿
    -0.06
    lichten
    -0.06
    伸æīĭ
    -0.06
    strip
    -0.06
    POSITIVE LOGITS
    ä¸Ģä½ĵæľº
    0.08
     misd
    0.07
    _INITIALIZER
    0.07
    adius
    0.07
    碳
    0.07
    ürn
    0.07
    à¦ŀà§į
    0.07
    СТÐIJ
    0.07
    _BEFORE
    0.07
    unte
    0.07
    Activations Density 0.012%

    No Known Activations