© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 777
    Prev
    Next
    INDEX
    Explanations

    say Spanish places

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

    No Comments

    Negative Logits
     Dakota
    -30.00
     Sioux
    -29.38
     Minnesota
    -29.25
     Nebraska
    -28.00
     Kansas
    -26.88
     Hawaii
    -26.88
     Iowa
    -25.88
     Hawai
    -25.25
    中美
    -24.88
    Kansas
    -24.63
    POSITIVE LOGITS
     Catalonia
    36.00
    西班牙
    35.50
     Catalan
    35.50
     Spain
    34.50
     Barcelona
    34.00
     Madrid
    32.75
    Spain
    31.88
     €
    30.63
    地中海
    30.38
     Sevilla
    29.75
    Activations Density 0.189%

    No Known Activations