© 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. 9837
    Prev
    Next
    INDEX
    Explanations

    Olympics, Super Bowl, Cup, Series

    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
    ByKey
    -0.08
    wad
    -0.08
    onge
    -0.08
    伯ä¹IJ
    -0.07
     ×ŀ×IJ×ķ×ĵ
    -0.07
    stown
    -0.07
    zut
    -0.07
    ç±»
    -0.07
    ##_
    -0.07
     agg
    -0.07
    POSITIVE LOGITS
    åı²ä¸ĬæľĢ
    0.09
    åı²ä¸Ĭ
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    Rare
    0.08
    åİĨåı²ä¸ĬçļĦ
    0.08
    åı²ä¸ĬçļĦ
    0.07
     Rare
    0.07
    à¹Ĥà¸ķ
    0.07
     rare
    0.07
     Idea
    0.07
    Activations Density 0.334%

    No Known Activations