© 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. 1427
    Prev
    Next
    INDEX
    Explanations

    say "European"

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

    No Comments

    Negative Logits
    [token
    -26.75
    token
    -25.50
    .getToken
    -24.63
     token
    -24.50
    -token
    -24.25
    tokens
    -24.00
     Tokens
    -23.75
     tokens
    -23.63
    	token
    -23.50
    电机
    -23.38
    POSITIVE LOGITS
    欧洲
    19.38
     European
    19.25
    丹麦
    18.25
     browser
    17.50
     Browser
    17.13
    波兰
    17.00
    European
    16.50
     Poland
    16.38
     browsers
    16.38
     europe
    16.13
    Activations Density 0.265%

    No Known Activations