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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2292
    Prev
    Next
    INDEX
    Explanations

    say "coup"

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

    No Comments

    Negative Logits
    民宿
    -19.00
    餐厅
    -18.75
    Visitor
    -18.50
    客房
    -18.00
     Airbnb
    -17.75
    酒业
    -17.63
    旅行社
    -17.50
     coaster
    -17.50
    conda
    -17.13
    商学院
    -17.00
    POSITIVE LOGITS
     elections
    18.38
    缅甸
    18.00
     electoral
    18.00
     election
    17.88
    执政
    17.63
     Duterte
    17.13
     Electoral
    16.38
     regime
    16.25
     presidential
    16.13
     Myanmar
    15.81
    Activations Density 0.396%

    No Known Activations