© 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. 574
    Prev
    Next
    INDEX
    Explanations

    say place names

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

    No Comments

    Negative Logits
     Venezuelan
    -24.63
     Venezuela
    -23.00
     Colombian
    -22.50
    (sigma
    -22.00
     Venezuel
    -21.50
     Saudis
    -21.13
     Saudi
    -20.50
     Niger
    -20.13
     Maduro
    -20.00
    σ
    -19.88
    POSITIVE LOGITS
     Boston
    52.25
    Boston
    50.00
     Massachusetts
    49.00
    福州
    47.50
    闽
    46.25
    漳州
    46.00
    厦门市
    44.00
    福建省
    43.00
    福建
    42.50
    厦门
    42.25
    Activations Density 0.128%

    No Known Activations