© 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. 1990
    Prev
    Next
    INDEX
    Explanations

    [手术] => [手术]

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

    No Comments

    Negative Logits
     surgical
    -41.50
     surgery
    -39.50
    手术
    -39.25
     Surgical
    -37.50
     Surgery
    -37.00
     surgeries
    -36.00
     surg
    -35.75
     Surg
    -27.50
    术
    -26.88
    術
    -26.00
    POSITIVE LOGITS
    珈
    16.88
    党员
    16.00
    灯
    15.13
    宝马
    14.50
    贞
    14.38
    .getCode
    14.31
    lights
    14.19
    诚信
    14.13
    咖啡
    14.00
     Alabama
    13.81
    Activations Density 0.081%

    No Known Activations