© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1090
    Prev
    Next
    INDEX
    Explanations

    [交易] => [交易]

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

    No Comments

    Negative Logits
     trade
    -27.13
     Trade
    -25.63
     TE
    -25.50
    _TE
    -24.88
     trades
    -24.38
     TX
    -22.88
     TRADE
    -22.63
     trading
    -22.25
     traded
    -22.25
    Tx
    -20.88
    POSITIVE LOGITS
    密码
    16.13
    龙泉
    15.94
    efs
    15.81
    inkel
    14.81
     Bul
    14.81
    ymb
    14.69
    陷阱
    14.56
     Word
    14.50
    _STAT
    14.13
    Designer
    14.13
    Activations Density 0.037%

    No Known Activations