© 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. 1944
    Prev
    Next
    INDEX
    Explanations

    say construction

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

    No Comments

    Negative Logits
     Western
    -33.75
    Western
    -31.50
     western
    -31.50
    西方
    -30.38
    West
    -29.63
     West
    -27.75
    Writing
    -27.63
     WEST
    -27.50
    writing
    -27.50
     Writing
    -27.50
    POSITIVE LOGITS
    建构
    15.88
     shots
    15.50
    施工
    15.44
    _tuple
    15.00
     construction
    15.00
    .construct
    14.94
    ól
    14.44
    olf
    14.38
    建筑
    14.13
     constructions
    13.81
    Activations Density 0.160%

    No Known Activations