© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 857
    Prev
    Next
    INDEX
    Explanations

    Central Asia

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

    No Comments

    Negative Logits
    湛江
    -32.50
    葡萄牙
    -29.13
    广东省
    -28.38
    江门
    -27.88
    广州市
    -27.75
    东莞
    -27.75
     Southampton
    -26.88
    在广州
    -26.50
     Miami
    -26.13
    湾区
    -26.13
    POSITIVE LOGITS
     Mongolia
    46.75
     Kazakhstan
    43.00
     Uzbek
    41.75
    蒙古
    40.00
     Afghan
    37.50
     Tibetan
    37.00
    青海
    36.25
    新疆
    36.00
     Mong
    35.50
     Tibet
    35.50
    Activations Density 0.205%

    No Known Activations