© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    say 外资

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

    No Comments

    Negative Logits
    伯
    -23.63
    mer
    -23.38
     Ber
    -22.88
     merit
    -22.63
     mer
    -22.25
    Ber
    -21.88
     Mer
    -21.38
    ber
    -20.75
     ber
    -20.63
     MER
    -20.50
    POSITIVE LOGITS
    资
    30.13
    外资
    21.88
     Capital
    21.88
     CAPITAL
    20.63
     capital
    19.88
    Mut
    19.88
    capital
    19.38
    Capital
    19.38
     pet
    19.00
     Mem
    18.88
    Activations Density 0.092%

    No Known Activations