© 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. 615
    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
     Fiji
    -27.75
     Samoa
    -27.63
     NZ
    -26.25
    新西兰
    -25.88
    (uuid
    -25.88
     Auckland
    -25.63
     Taliban
    -25.00
    磻
    -24.25
     Afghan
    -24.13
    宁夏
    -23.88
    POSITIVE LOGITS
     Detroit
    59.50
    Detroit
    52.75
     Michigan
    44.50
    Michigan
    42.00
    株洲
    35.75
    长沙
    35.50
    长沙市
    33.25
     Wolver
    31.88
    湘潭
    31.00
    合肥市
    29.88
    Activations Density 0.036%

    No Known Activations