© 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. 15372
    Prev
    Next
    INDEX
    Explanations

    say "Austrian"

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

    No Comments

    Negative Logits
    札
    -20.13
    izontal
    -19.38
     Quincy
    -18.63
    樱花
    -18.50
    Vertical
    -18.38
     trụ
    -18.25
    TagName
    -18.13
     Bamboo
    -17.75
     Vertical
    -17.50
     billboard
    -17.50
    POSITIVE LOGITS
     Austrian
    17.75
    奥地利
    16.13
    诸侯
    15.13
     Österreich
    14.19
    /rs
    13.69
    ensi
    13.25
    哈
    13.19
     Swedish
    12.88
    슬
    12.69
     tors
    12.56
    Activations Density 0.185%

    No Known Activations