© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1350
    Prev
    Next
    INDEX
    Explanations

    [font] => [value]

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

    No Comments

    Negative Logits
     font
    -55.75
    Font
    -53.50
    字体
    -52.25
     Font
    -52.00
    font
    -51.75
     fonts
    -50.50
    _font
    -48.50
    字
    -46.75
     FONT
    -46.50
    (font
    -46.00
    POSITIVE LOGITS
    遊
    15.75
     Safari
    14.00
     play
    13.81
    禺
    13.56
     Abraham
    13.44
     Ther
    13.44
    以色列
    13.31
    跳跃
    13.06
    -Israel
    12.94
     игров
    12.63
    Activations Density 0.071%

    No Known Activations