© 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. 1397
    Prev
    Next
    INDEX
    Explanations

    group => 书法

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

    No Comments

    Negative Logits
    书法
    -37.00
    书法家
    -24.88
    font
    -21.88
     letters
    -21.13
    FONT
    -20.88
     fonts
    -20.88
    字
    -20.50
    书
    -20.38
     Fonts
    -20.25
    字体
    -20.25
    POSITIVE LOGITS
     Gaza
    15.81
    哥伦比亚
    15.75
    港
    15.00
    工具
    14.56
     Theodore
    14.19
    泉州
    14.00
     tool
    13.44
    嵬
    13.25
     TOOL
    13.25
    濟
    13.19
    Activations Density 0.049%

    No Known Activations