© 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. 558
    Prev
    Next
    INDEX
    Explanations

    say Chinese locations

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

    No Comments

    Negative Logits
     Sass
    -23.50
     Jakarta
    -22.50
     JAVA
    -21.50
     Sakura
    -21.38
     Azerbai
    -21.38
     Yemen
    -21.38
     Riyadh
    -20.75
    贝壳
    -20.25
    骊
    -20.00
     Saudis
    -19.88
    POSITIVE LOGITS
    湖北省
    71.50
    湖北
    68.50
    武汉
    64.00
    武汉市
    61.75
    楚
    60.50
    宜昌
    59.75
     Irish
    59.75
    鄂
    56.00
    襄阳
    55.75
     Dublin
    55.25
    Activations Density 0.273%

    No Known Activations