© 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. 697
    Prev
    Next
    INDEX
    Explanations

    say "Paul"

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

    No Comments

    Negative Logits
     Delhi
    -26.50
     Mustang
    -25.75
    Colorado
    -24.63
    呼和浩特
    -24.25
     Kashmir
    -23.50
     Bollywood
    -23.25
     Colorado
    -23.13
    遵义
    -23.13
     Lahore
    -22.88
     Pakistani
    -22.50
    POSITIVE LOGITS
     Paul
    20.00
    海岛
    19.75
    保罗
    19.75
     ε
    19.25
     κ
    18.88
     Greek
    18.38
    希腊
    18.38
     Corinthians
    17.75
    κ
    17.00
    海岸
    17.00
    Activations Density 0.180%

    No Known Activations