© 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. 585
    Prev
    Next
    INDEX
    Explanations

    say "place names"

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

    No Comments

    Negative Logits
    豆
    -22.38
     French
    -21.63
    法国
    -21.50
    广西
    -21.25
    邕
    -21.13
     Bourbon
    -21.00
    泰国
    -20.75
    南宁市
    -20.63
    丹麦
    -20.38
    南宁
    -20.25
    POSITIVE LOGITS
     Ruiz
    23.88
    秭
    22.00
     Torres
    21.13
    邗
    19.63
     Vancouver
    19.25
    扬
    18.88
     Rotterdam
    18.63
    延安
    18.00
    埔
    17.75
    Van
    17.63
    Activations Density 0.524%

    No Known Activations