© 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. 1846
    Prev
    Next
    INDEX
    Explanations

    calligraphy styles

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

    No Comments

    Negative Logits
    字
    -22.88
    Byte
    -21.50
    FONT
    -20.38
     字
    -20.25
    字体
    -19.88
     Byte
    -19.50
     Berm
    -18.13
     Brain
    -18.13
    GraphNode
    -17.88
    font
    -17.63
    POSITIVE LOGITS
    jee
    14.50
    Jo
    14.38
     financial
    13.88
    工作报告
    13.13
    cean
    13.06
     Job
    12.88
    afe
    12.88
    安全
    12.56
     log
    12.44
    金融
    12.25
    Activations Density 0.065%

    No Known Activations