© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    施工

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

    No Comments

    Negative Logits
    施工
    -37.25
     construction
    -33.00
     constructions
    -29.63
    Construction
    -29.38
    工程施工
    -29.25
     Construction
    -28.75
     construct
    -27.50
    construct
    -26.75
    construction
    -26.75
     constructs
    -25.50
    POSITIVE LOGITS
     AL
    18.13
     European
    17.50
    _maps
    16.50
    oge
    16.25
     alphabet
    16.00
     Fairy
    15.81
    <Float
    15.75
    ALE
    15.69
    英
    15.44
    .getMap
    15.44
    Activations Density 0.033%

    No Known Activations