© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    further relates

    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
    骤
    -0.08
    innacle
    -0.08
    ãĥ¤ãĥ¼
    -0.08
    ingly
    -0.07
    veau
    -0.07
    é©Ł
    -0.07
    resent
    -0.07
    bbe
    -0.06
    åľ¨
    -0.06
    ãĥ¥
    -0.06
    POSITIVE LOGITS
    Ø©
    0.11
    eenth
    0.10
    nya
    0.10
    çļĦ
    0.10
    trag
    0.09
    ÑģÑı
    0.09
    entication
    0.09
    agraph
    0.09
    ìĿĦ
    0.08
    ÛĮ
    0.08
    Activations Density 0.002%

    No Known Activations