© 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. 1546
    Prev
    Next
    INDEX
    Explanations

    工艺 => 工艺

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

    No Comments

    Negative Logits
    工艺
    -39.75
     Policy
    -27.63
    政策
    -27.38
     policy
    -26.50
    生产工艺
    -26.38
    Policy
    -25.25
     Policies
    -24.75
     policies
    -24.63
    policy
    -24.50
    工艺品
    -23.88
    POSITIVE LOGITS
    -football
    17.25
    .getHeader
    16.75
    Float
    16.63
    Vector
    16.38
    vector
    15.81
     football
    15.63
     Football
    15.44
     float
    15.44
    .vector
    15.00
    足球
    14.69
    Activations Density 0.033%

    No Known Activations