© 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. 41141
    Prev
    Next
    INDEX
    Explanations

    multivariate dimensions

    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
     Rail
    -0.08
    订
    -0.07
    ankan
    -0.07
    -end
    -0.07
    иÑĤоÑĢ
    -0.07
    _between
    -0.07
    éĶĦ
    -0.07
    æĹ¥æĹ©ä¸Ĭ
    -0.07
     rail
    -0.07
    éĩı身
    -0.07
    POSITIVE LOGITS
     coordinates
    0.12
    coordinates
    0.10
    ä¸īç»´
    0.09
     directions
    0.09
    åĿIJæłĩ
    0.09
    æĭīå¾·
    0.08
     Coordinates
    0.08
    åĽĽç»´
    0.08
    Coordinates
    0.08
     volume
    0.08
    Activations Density 0.020%

    No Known Activations