© 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. 11075
    Prev
    Next
    INDEX
    Explanations

    URLs and code fragments

    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
    <|box_end|>
    -0.11
     muit
    -0.10
    ä¸įå®ĮçļĦ
    -0.10
    ohner
    -0.09
    ualan
    -0.09
    æĻ¨æĬ¥
    -0.09
    ÅĤuga
    -0.09
    ascript
    -0.08
    æ³ķç½ij
    -0.08
    empa
    -0.08
    POSITIVE LOGITS
    a
    0.11
    s
    0.09
    ar
    0.09
    en
    0.09
    e
    0.09
    A
    0.09
    u
    0.09
    T
    0.09
    L
    0.09
    C
    0.08
    Activations Density 0.067%

    No Known Activations