© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15286
    Prev
    Next
    INDEX
    Explanations

    say Hawaiian words

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

    No Comments

    Negative Logits
     دمشق
    -19.63
    gars
    -18.63
     Synd
    -17.75
    dig
    -17.63
    樘
    -16.38
    цеп
    -16.38
    slick
    -16.25
    楼梯
    -16.25
    _cos
    -16.13
    _corners
    -16.13
    POSITIVE LOGITS
     Hawaii
    30.25
     Hawaiian
    29.75
     Hawai
    29.13
     Maui
    27.50
    ʻ
    20.75
     Honolulu
    19.75
     Samoa
    19.63
    屿
    18.88
     lua
    18.75
    蕉
    18.75
    Activations Density 0.079%

    No Known Activations