© 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. 773
    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
     Lebanese
    -32.50
     Beirut
    -27.13
     Hezbollah
    -27.13
     Iranian
    -21.63
     Pyongyang
    -21.13
     Lebanon
    -21.13
    邙
    -21.13
     Syrians
    -21.00
     Iranians
    -21.00
    三亚
    -20.88
    POSITIVE LOGITS
     Wisconsin
    64.00
    安徽省
    55.00
     Milwaukee
    53.25
    芜湖
    51.75
    安徽
    51.00
    皖
    49.25
    合肥
    45.75
    歙
    45.50
    合肥市
    44.75
    波兰
    44.00
    Activations Density 0.072%

    No Known Activations