© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17897
    Prev
    Next
    INDEX
    Explanations

    code snippets with '0' or '1'

    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
    ian
    -0.08
    in
    -0.07
    ↵
    -0.07
    im
    -0.07
    à¸ģาร
    -0.07
    ãĤĪãģĨãģª
    -0.07
    (
    -0.07
    ä¸Ģ个
    -0.06
    th
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    декваÑĤ
    0.09
    zinho
    0.09
    aruhi
    0.09
    uet
    0.08
    sweise
    0.08
    -bodied
    0.08
    ::$
    0.08
    istik
    0.08
    aced
    0.08
    ÑģоÑĢ
    0.08
    Activations Density 0.039%

    No Known Activations