© 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. 411
    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
    该县
    -24.13
     provinces
    -22.75
    省份
    -22.50
    省政府
    -21.00
     province
    -20.38
    我省
    -20.38
    省内
    -20.25
     Provincial
    -20.25
     provincial
    -20.13
    省
    -19.50
    POSITIVE LOGITS
     Seattle
    42.50
    Seattle
    41.00
     Atlanta
    38.50
    青岛市
    36.50
    Atlanta
    36.00
    青岛
    36.00
    广州
    35.50
     Minneapolis
    34.50
     Houston
    34.50
     Chicago
    34.00
    Activations Density 0.166%

    No Known Activations