© 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. 418
    Prev
    Next
    INDEX
    Explanations

    say US politicians

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

    No Comments

    Negative Logits
    赣
    -20.25
     Portuguese
    -20.13
     Osaka
    -20.00
    顺德
    -19.25
    .dk
    -19.25
    インド
    -19.13
    kart
    -18.63
     São
    -18.50
     Má
    -18.13
    INET
    -17.88
    POSITIVE LOGITS
    白宫
    33.50
    特朗普
    31.13
     Obama
    31.00
    拜登
    31.00
    奥巴马
    30.50
    Obama
    29.00
     Biden
    27.88
     Washington
    27.63
     Boehner
    27.38
    华盛顿
    26.75
    Activations Density 0.731%

    No Known Activations