© 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. 525
    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
    镇江
    -21.00
     Newark
    -20.00
     Santana
    -19.63
    (tf
    -18.63
    NECT
    -18.38
     Southampton
    -18.25
     Harlem
    -17.50
     Burlington
    -17.38
     TF
    -16.75
     Essex
    -15.94
    POSITIVE LOGITS
    澳洲
    47.75
     Australian
    47.00
     Australia
    46.50
     Aussie
    46.50
     Australians
    46.25
    澳大利亚
    46.25
    Australian
    44.25
    Australia
    44.25
    澳
    39.50
    悉尼
    38.25
    Activations Density 0.148%

    No Known Activations