© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1844
    Prev
    Next
    INDEX
    Explanations

    say "pixel"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     South
    -36.00
    South
    -36.00
    south
    -30.00
     SOUTH
    -29.75
    南
    -29.63
     south
    -27.25
    南方
    -26.13
    Southern
    -25.50
     Süd
    -23.13
     Southern
    -22.88
    POSITIVE LOGITS
    像素
    20.38
     pixels
    16.38
    纤维
    16.13
     Caesar
    16.00
    信用
    15.63
    _pixels
    15.56
     pixel
    15.31
    鸿
    14.88
    pixel
    14.81
    _pixel
    14.56
    Activations Density 0.200%

    No Known Activations