© 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. 937
    Prev
    Next
    INDEX
    Explanations

    say "north/south"

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

    No Comments

    Negative Logits
    江苏省
    -26.25
     Belgian
    -23.63
    常州
    -22.75
    ngx
    -22.50
    江苏
    -22.25
     Croatian
    -21.88
     Nairobi
    -21.38
     Czech
    -20.88
     Kenya
    -20.75
     Taiwanese
    -20.13
    POSITIVE LOGITS
     northern
    18.88
     southern
    18.50
    �
    18.38
     Northern
    17.88
     Grey
    17.25
    south
    17.00
    北
    17.00
    South
    16.75
     south
    16.50
    ith
    16.25
    Activations Density 0.028%

    No Known Activations