© 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. 482
    Prev
    Next
    INDEX
    Explanations

    say Hawaiian

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

    No Comments

    Negative Logits
    邯郸
    -30.50
    邢台
    -26.75
     Damascus
    -26.75
    沈阳
    -26.38
     Romanian
    -26.38
     Syrians
    -26.00
    漯
    -25.50
    河北
    -24.88
     Trafford
    -24.63
     دمشق
    -24.63
    POSITIVE LOGITS
     Hawaiian
    64.00
     Hawai
    62.00
     Hawaii
    60.75
     Honolulu
    57.50
     Maui
    50.75
     lua
    41.75
     Guam
    40.50
     Fiji
    40.25
     Lua
    39.50
    lua
    37.50
    Activations Density 0.127%

    No Known Activations