© 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. 1435
    Prev
    Next
    INDEX
    Explanations

    say "foreign country"

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

    No Comments

    Negative Logits
    韩国
    -37.75
     Korea
    -36.25
    是韩国
    -36.25
    韓
    -36.25
     Korean
    -36.00
    韩
    -32.25
     Koreans
    -31.88
    朝鲜
    -29.50
     Kim
    -24.63
     Hàn
    -24.50
    POSITIVE LOGITS
     Buckingham
    20.25
     cloud
    20.00
     Musk
    19.38
     Ca
    19.25
    雲
    19.13
    云
    18.75
     Cloud
    18.00
    蛋白
    18.00
    Pixels
    17.88
     Aws
    17.88
    Activations Density 0.093%

    No Known Activations