© 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. 715
    Prev
    Next
    INDEX
    Explanations

    say "medieval"

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

    No Comments

    Negative Logits
     Honolulu
    -30.63
     Taiwanese
    -26.88
    杭州市
    -26.25
     Hawai
    -24.63
     Singapore
    -24.13
    Singapore
    -24.00
     Taipei
    -24.00
     Karachi
    -23.75
     Brisbane
    -23.63
     Hawaii
    -23.50
    POSITIVE LOGITS
     medieval
    27.75
     Medieval
    26.50
    骑士
    22.25
    封建
    18.13
     Crus
    17.75
    ITAL
    17.50
    意大利
    17.50
    ddf
    17.38
    oir
    17.00
    €
    17.00
    Activations Density 0.370%

    No Known Activations