© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1419
    Prev
    Next
    INDEX
    Explanations

    do not say government

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

    No Comments

    Negative Logits
     government
    -34.75
    政府
    -34.00
     governments
    -33.75
     Governments
    -33.75
    Government
    -33.50
     Government
    -32.75
    government
    -31.63
     governmental
    -31.13
    政府部门
    -27.25
    中国政府
    -26.13
    POSITIVE LOGITS
     cardinal
    16.63
    骑
    15.06
    ট
    14.88
    兵马
    14.75
     bik
    14.38
    bic
    14.31
    僧
    14.13
     Pdf
    14.06
     sắc
    14.00
     pdf
    13.94
    Activations Density 0.217%

    No Known Activations