© 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. 28597
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    à¦ľà§ĩ
    -0.07
    ัà¸Ķสà¹Īวà¸Ļ
    -0.07
    YST
    -0.07
    etty
    -0.07
    çİĩé«ĺ
    -0.07
     Cats
    -0.07
    ingleton
    -0.06
    yadi
    -0.06
    æ»ģ
    -0.06
    erville
    -0.06
    POSITIVE LOGITS
    лÑĮÑĦ
    0.08
     soft
    0.08
    ênh
    0.07
    ceeded
    0.07
    软
    0.07
    广å®ī
    0.07
    åIJĮèĥŀ
    0.07
    æ´»äºĨ
    0.06
    дÑĢа
    0.06
    soft
    0.06
    Activations Density 0.019%

    No Known Activations