© 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. 516
    Prev
    Next
    INDEX
    Explanations

    Michigan

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

    No Comments

    Negative Logits
     Buenos
    -29.88
     Lahore
    -26.38
     Argentine
    -26.13
    阿根廷
    -25.75
     Puerto
    -25.75
     Taliban
    -25.63
    天津市
    -25.50
     Islamabad
    -25.25
    蓟
    -25.13
     Argentina
    -24.50
    POSITIVE LOGITS
     Michigan
    60.75
    Michigan
    58.50
     Detroit
    41.75
     Lansing
    41.75
    安徽省
    37.25
     Wolver
    37.25
    安庆
    36.75
     CX
    36.25
    安徽
    36.25
    Detroit
    36.00
    Activations Density 0.067%

    No Known Activations