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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 159
    Prev
    Next
    INDEX
    Explanations

    say Spanish words

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

    No Comments

    Negative Logits
    连云港
    -21.13
    秦皇岛
    -19.75
    太湖
    -19.63
    山西省
    -19.63
    昆山
    -18.50
    淮安
    -18.25
    扬州
    -17.88
    东海
    -17.75
    常州
    -17.75
    徐州
    -17.75
    POSITIVE LOGITS
    墨西哥
    55.25
    西班牙
    54.75
     Spanish
    49.25
    阿根廷
    48.50
     Mexico
    48.50
    涪
    48.00
     Mexican
    47.25
    Mexico
    46.50
     Colombian
    45.75
     García
    45.75
    Activations Density 2.881%

    No Known Activations