© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    [Gender] => [Law]

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

    No Comments

    Negative Logits
     gender
    -37.50
     Gender
    -34.50
    Gender
    -32.75
    性别
    -32.75
    gender
    -32.75
     genders
    -27.88
    _gender
    -26.38
    .gender
    -26.25
    genes
    -24.00
    几何
    -22.13
    POSITIVE LOGITS
     law
    17.88
     Law
    17.75
    Maps
    17.25
     Maps
    16.88
    Law
    16.38
    law
    15.81
    法
    15.69
     AFP
    15.63
    _paper
    15.56
    档案
    15.31
    Activations Density 0.081%

    No Known Activations