© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 971
    Prev
    Next
    INDEX
    Explanations

    Balkan countries

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     df
    -29.63
     Chicago
    -29.13
    (df
    -28.88
    	df
    -27.75
    .df
    -27.50
    Chicago
    -27.25
    惠州
    -27.25
    东莞
    -27.13
    汕头
    -26.75
    在广州
    -26.63
    POSITIVE LOGITS
     Alban
    47.75
     Kosovo
    44.75
     Albania
    44.50
     Macedonia
    28.50
    Georgia
    26.00
     Georgia
    26.00
    湘西
    26.00
     Ethiopian
    25.88
     Georgian
    25.63
     Scots
    24.88
    Activations Density 0.027%

    No Known Activations