© 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. 60343
    Prev
    Next
    INDEX
    Explanations

    spatial dimensions and grid structures

    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
    æ´Ľä¼Ĭ
    -0.09
    æ²¿æ±Ł
    -0.09
    è¶Ł
    -0.08
    åħ¨éķ¿
    -0.08
    INGER
    -0.08
    UME
    -0.07
    èħ¸
    -0.07
    èĤł
    -0.07
    è´¯
    -0.07
    à¸Ĭà¹Īวà¸ĩ
    -0.07
    POSITIVE LOGITS
     grid
    0.09
    grid
    0.09
    .grid
    0.08
    _grid
    0.08
    ç½ijæł¼
    0.08
    corner
    0.08
    Grid
    0.08
    Corner
    0.08
    对产åĵģ
    0.08
     coordinates
    0.08
    Activations Density 0.157%

    No Known Activations