© 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. 879
    Prev
    Next
    INDEX
    Explanations

    say Australia

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

    No Comments

    Negative Logits
    西甲
    -22.00
    巴萨
    -20.88
     Hispan
    -20.88
     Sevilla
    -20.88
     Venezuelan
    -20.00
    运河
    -20.00
    德州
    -19.50
     Hamm
    -19.00
     Sanchez
    -18.63
     Barcelona
    -18.50
    POSITIVE LOGITS
     Australian
    62.25
     Australia
    60.25
    Australian
    60.00
     Australians
    59.75
    澳大利亚
    59.25
    澳洲
    56.25
    Australia
    56.25
     Aussie
    52.25
     Melbourne
    52.00
     Sydney
    51.00
    Activations Density 1.028%

    No Known Activations