© 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. 684
    Prev
    Next
    INDEX
    Explanations

    say locations

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

    No Comments

    Negative Logits
     Kag
    -24.75
     NSK
    -23.25
    金陵
    -20.50
    南京市
    -20.50
    菏泽
    -20.13
     Berkshire
    -19.88
    溧
    -19.88
    亳
    -19.63
    徐州
    -19.38
     Ames
    -18.75
    POSITIVE LOGITS
    海南
    69.50
    海南省
    68.50
    三亚
    58.75
    儋
    57.00
    海口
    56.25
    椰
    55.00
    琼
    51.75
     Florida
    51.00
    Florida
    48.75
    南海网
    47.75
    Activations Density 0.065%

    No Known Activations