© 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. 1025
    Prev
    Next
    INDEX
    Explanations

    [建设] => [建设]

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

    No Comments

    Negative Logits
     construction
    -31.25
    建设
    -30.00
    建設
    -29.88
     Construction
    -27.88
    construction
    -27.75
     constructions
    -26.75
     construct
    -26.38
    construct
    -26.38
    Construction
    -26.25
     building
    -25.50
    POSITIVE LOGITS
    ar
    18.38
    nal
    17.63
     radio
    17.00
    _window
    15.63
    -radio
    15.19
    windows
    14.81
    .radio
    14.81
    农
    14.50
     Radio
    14.50
    gui
    14.44
    Activations Density 0.079%

    No Known Activations