© 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. 40
    Prev
    Next
    INDEX
    Explanations

    say "US political terms"

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

    No Comments

    Negative Logits
     Belgium
    -24.25
    赣
    -24.25
    南昌
    -24.13
    比利时
    -24.00
    赣州
    -23.88
     Czech
    -23.88
    江西
    -23.50
    九江
    -23.25
    常州
    -22.75
    江西省
    -22.75
    POSITIVE LOGITS
    白宫
    26.75
    拜登
    25.75
     Washington
    24.88
    在美国
    24.13
    Washington
    22.88
    美国
    22.75
     USDA
    22.75
    华盛顿
    21.75
    Federal
    21.63
     Congressional
    21.50
    Activations Density 0.687%

    No Known Activations