© 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. 915
    Prev
    Next
    INDEX
    Explanations

    say city names

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

    No Comments

    Negative Logits
    沪
    -29.00
    在上海
    -25.63
    上海市
    -25.00
    鞍山
    -23.63
     NSW
    -22.38
    上海
    -22.25
    厦
    -21.13
     Sydney
    -21.00
     Milano
    -20.75
    悉尼
    -20.25
    POSITIVE LOGITS
    潍
    32.50
    扬州
    30.25
    潍坊
    28.38
     Iowa
    28.25
    德州
    28.13
     Tulsa
    27.63
    邗
    27.25
     Wichita
    26.25
     Oklahoma
    26.00
    泰州
    26.00
    Activations Density 0.081%

    No Known Activations