© 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. 1937
    Prev
    Next
    INDEX
    Explanations

    [疫情] => [疫情]

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

    No Comments

    Negative Logits
    疫情
    -25.38
    新冠疫情
    -23.63
    疫情影响
    -20.88
    疫情防控
    -20.25
    新冠肺炎
    -20.00
    影视剧
    -18.25
    COVID
    -17.63
     COVID
    -17.63
    疫情期间
    -17.13
     Covid
    -16.25
    POSITIVE LOGITS
     sigma
    18.50
    大豆
    18.00
     Buck
    17.63
     buc
    17.13
     buck
    16.75
    /ws
    16.63
    .ws
    16.38
     kart
    15.94
    法
    15.19
    木
    14.81
    Activations Density 0.045%

    No Known Activations