© 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. 779
    Prev
    Next
    INDEX
    Explanations

    say US places

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

    No Comments

    Negative Logits
     Iranian
    -31.38
     Iran
    -30.88
     Iranians
    -28.75
    Iran
    -26.00
     Australian
    -25.63
    伊朗
    -25.50
     Australia
    -25.50
     Aussie
    -25.38
    澳洲
    -25.13
    Australian
    -24.88
    POSITIVE LOGITS
     Yankees
    22.63
     Maine
    22.38
     Yankee
    21.75
     Cadillac
    20.88
     Puerto
    20.25
    Md
    19.38
     Maryland
    19.25
     Niagara
    18.75
     Harlem
    18.00
     Baltimore
    17.50
    Activations Density 0.070%

    No Known Activations