© 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. 48827
    Prev
    Next
    INDEX
    Explanations

    rugby tours and categories

    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
    稿件æĿ¥æºIJ
    -0.07
    americ
    -0.07
    è±¹
    -0.07
    acific
    -0.07
    egin
    -0.07
    ampu
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    -0.07
    aptive
    -0.06
    althy
    -0.06
    POSITIVE LOGITS
    ä¸ĩåı¤
    0.08
    天ä»Ļ
    0.07
    yam
    0.07
    åı¯ä»¥æĮīçħ§
    0.07
    ot
    0.07
    ken
    0.07
    ding
    0.06
    imba
    0.06
    èİİ
    0.06
    æĽ´å¥½çļĦ
    0.06
    Activations Density 0.004%

    No Known Activations