© 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. 470
    Prev
    Next
    INDEX
    Explanations

    say places

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

    No Comments

    Negative Logits
    张家口
    -34.25
     DC
    -29.00
    河北省
    -27.88
    涞
    -27.75
    承德
    -27.38
    海淀
    -26.00
     Mongolia
    -25.25
    莜
    -24.88
    廊坊
    -24.63
     dc
    -24.25
    POSITIVE LOGITS
    长沙
    40.00
    长沙市
    36.00
     Marseille
    33.25
    株洲
    30.25
    东莞市
    30.13
    东莞
    29.38
    利物浦
    28.50
     Maharashtra
    27.25
    Detroit
    25.38
     Mumbai
    25.13
    Activations Density 0.099%

    No Known Activations