© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14839
    Prev
    Next
    INDEX
    Explanations

    Nazism

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    кат
    -18.50
    青铜
    -18.13
     Transactions
    -17.63
    )Math
    -17.25
     Philadelphia
    -17.00
    湿地
    -17.00
    合作伙伴
    -16.88
     dilig
    -16.88
    湖泊
    -16.75
    SQLite
    -16.50
    POSITIVE LOGITS
     Hitler
    23.00
    Hit
    22.63
     hit
    19.50
    .Hit
    18.50
     Nazis
    18.25
     Nazi
    17.88
    种族
    17.75
     Hit
    17.63
    -hit
    17.25
     hate
    17.00
    Activations Density 0.171%

    No Known Activations