© 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. 423
    Prev
    Next
    INDEX
    Explanations

    say Southeast Asian countries

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

    No Comments

    Negative Logits
    张家口
    -23.63
     Erie
    -22.88
    奥地利
    -22.63
     Pennsylvania
    -22.00
    Ohio
    -21.75
     Pittsburgh
    -21.38
    冬奥
    -20.63
     Austrian
    -20.25
     Österreich
    -20.13
     Belfast
    -19.75
    POSITIVE LOGITS
     Malaysian
    59.00
     Indonesian
    57.75
     Malay
    56.25
    印尼
    55.25
     Malaysia
    55.25
    马来西亚
    54.75
     Malays
    54.00
     Thai
    54.00
     Thailand
    52.75
     Indonesia
    51.75
    Activations Density 0.997%

    No Known Activations