© 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. 21008
    Prev
    Next
    INDEX
    Explanations

    titles and roles followed by names

    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
    ä¸įä¼ij
    -0.07
    DEX
    -0.07
    benh
    -0.07
    legate
    -0.07
    ÙĪا
    -0.07
    EAN
    -0.07
     Kapol
    -0.06
     Golk
    -0.06
    .bd
    -0.06
    ç»´å°Ķ
    -0.06
    POSITIVE LOGITS
    hib
    0.07
    vient
    0.06
    ÑģÑĤавлÑı
    0.06
    Õ
    0.06
    atamente
    0.06
    whatever
    0.06
    સà«į
    0.06
    æĿ¥å¾Ĺ
    0.06
    ηÏĥη
    0.06
    (rawValue
    0.06
    Activations Density 2.113%

    No Known Activations