© 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. 31676
    Prev
    Next
    INDEX
    Explanations

    almost everything/all

    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
    并èĮĤ
    -0.11
    <|box_end|>
    -0.11
    etje
    -0.10
    igits
    -0.10
    stry
    -0.09
     ä»ĬæĹ¥ãĤĤ
    -0.09
    ÑģÑĤан
    -0.09
     ãģ¾ãģ¨
    -0.09
    IGGER
    -0.09
    pected
    -0.09
    POSITIVE LOGITS
    ly
    0.10
    nya
    0.07
    s
    0.07
    ments
    0.06
    ÛĮ
    0.06
    (
    0.06
    mente
    0.06
    al
    0.06
    a
    0.06
    ed
    0.06
    Activations Density 0.032%

    No Known Activations