© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    say "capital"

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

    No Comments

    Negative Logits
    义
    -17.88
     erb
    -16.50
     stmt
    -16.38
    義
    -15.88
    辕
    -15.13
    实习生
    -14.69
     loc
    -14.56
    .Msg
    -14.38
    [loc
    -14.38
     seq
    -14.19
    POSITIVE LOGITS
     capital
    92.50
    资本
    90.50
     Capital
    87.50
    Capital
    85.00
    capital
    84.00
     CAPITAL
    74.00
    (cap
    72.50
    Cap
    72.00
    -capital
    71.50
     cap
    70.50
    Activations Density 0.320%

    No Known Activations