© 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. 720
    Prev
    Next
    INDEX
    Explanations

    say Hungarian words

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

    No Comments

    Negative Logits
    茂名
    -31.50
    汕
    -26.50
    湾区
    -25.13
    湛江
    -25.13
    广东省
    -24.13
    南海
    -23.38
    佛山市
    -23.13
    珠海
    -22.88
    广东
    -22.75
    北海
    -22.38
    POSITIVE LOGITS
     Hungarian
    69.00
     Hungary
    64.00
    匈
    61.50
     Budapest
    57.75
    Hung
    48.00
     Slovak
    47.50
     Sz
    44.50
     Slovakia
    41.00
     Romanian
    40.25
    Sz
    40.00
    Activations Density 0.115%

    No Known Activations