© 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. 475
    Prev
    Next
    INDEX
    Explanations

    say Colombia

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

    No Comments

    Negative Logits
    湖北省
    -23.75
    鄂
    -22.00
    湖北
    -20.75
    宁波
    -20.13
    武汉
    -20.00
     PX
    -19.75
    台州
    -19.63
    武汉市
    -19.25
    hx
    -19.13
    gx
    -18.38
    POSITIVE LOGITS
     Colombian
    54.25
     Colombia
    50.00
     colomb
    41.50
     Colomb
    41.00
    哥伦比亚
    40.00
     Columbia
    35.75
    昆明
    34.75
    云南省
    34.50
    云南
    33.75
    滇
    32.25
    Activations Density 0.062%

    No Known Activations