© 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. 50274
    Prev
    Next
    INDEX
    Explanations

    dimensions or matrix size

    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
    illard
    -0.09
    à¸Ĩ
    -0.07
    èĮ§
    -0.07
    ÙĪائ
    -0.07
    åħĭç¦ı
    -0.07
    åħīæĺ¯
    -0.07
    -strokes
    -0.07
    WebpackPlugin
    -0.06
    æĪŁ
    -0.06
    ×ķ×ĵ×Ķ
    -0.06
    POSITIVE LOGITS
    纵
    0.08
    横
    0.07
    anzas
    0.07
    ä¸ĢæıIJ
    0.07
     vertically
    0.07
     ÃĹ
    0.06
    plex
    0.06
     numRows
    0.06
    atrix
    0.06
     "*",
    0.06
    Activations Density 0.042%

    No Known Activations