© 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. 20615
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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
    isata
    -0.07
    iski
    -0.07
    .gravity
    -0.06
    ä¸Ģ空
    -0.06
     rects
    -0.06
    asını
    -0.06
     rist
    -0.06
    -toggler
    -0.06
    è¿ĺæĺ¯ä¸ª
    -0.06
    ä¸įå¾Ĺ使çĶ¨
    -0.06
    POSITIVE LOGITS
    UCH
    0.08
     unpublished
    0.07
     assemb
    0.07
    çĿĢåij¢
    0.07
    æİĮä¸Ĭ
    0.07
    ozn
    0.07
    å°¼äºļ
    0.07
    åĪ«æľī
    0.06
    nhard
    0.06
    à¸ªà¸±à¸Ľà¸Ķาหà¹Į
    0.06
    Activations Density 0.070%

    No Known Activations