© 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. 656
    Prev
    Next
    INDEX
    Explanations

    say "proper nouns"

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

    No Comments

    Negative Logits
    浦东
    -25.13
     Austrian
    -22.63
    上海市
    -22.50
     Hungarian
    -22.13
    匈
    -22.00
    上海
    -21.63
    在上海
    -21.63
    奥地利
    -21.50
     Budapest
    -21.50
     Lomb
    -21.50
    POSITIVE LOGITS
    浯
    20.25
    佤
    20.13
     XML
    19.00
     Papua
    18.00
     Cameroon
    18.00
    soap
    17.50
    云南
    17.38
    XML
    17.38
    /xml
    17.00
     PostgreSQL
    16.75
    Activations Density 0.134%

    No Known Activations