© 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. 1512
    Prev
    Next
    INDEX
    Explanations

    字

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

    No Comments

    Negative Logits
    字
    -61.00
     字
    -45.00
    字体
    -40.50
     font
    -38.75
    文字
    -38.00
    font
    -36.25
    汉字
    -35.00
     Byte
    -34.75
     fonts
    -34.75
     byte
    -34.00
    POSITIVE LOGITS
    -engine
    17.38
    工程
    16.50
     engineering
    16.50
    PF
    16.25
    గ
    15.56
    engine
    15.44
     CPF
    15.13
    (engine
    15.06
    Engine
    14.81
    苏联
    14.75
    Activations Density 0.093%

    No Known Activations