© 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. 1742
    Prev
    Next
    INDEX
    Explanations

    [London] => [place]

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

    No Comments

    Negative Logits
     London
    -43.25
    伦敦
    -40.25
    London
    -38.00
     london
    -37.00
     Lond
    -32.25
    lambda
    -27.13
     England
    -26.75
     lambda
    -26.63
    λ
    -25.00
     (£
    -24.75
    POSITIVE LOGITS
    	script
    17.88
    Script
    16.50
    (di
    16.50
    /script
    16.50
     di
    15.94
    ẩu
    14.88
    (script
    14.75
    /art
    14.63
    arda
    14.63
    script
    14.56
    Activations Density 0.051%

    No Known Activations