© 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. 1682
    Prev
    Next
    INDEX
    Explanations

    legal compliance

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

    No Comments

    Negative Logits
     legal
    -63.75
    法律
    -59.00
     Legal
    -57.25
    Legal
    -56.25
    legal
    -54.25
     legally
    -49.25
    _legal
    -43.50
     legality
    -41.75
    /legal
    -40.75
    LEGAL
    -37.25
    POSITIVE LOGITS
    arth
    17.88
    炜
    14.56
    Ars
    14.31
    奥运会
    14.25
    askets
    14.19
     Sno
    14.06
    瞽
    13.94
    .DataVisualization
    13.69
    bios
    13.63
    /io
    13.31
    Activations Density 0.114%

    No Known Activations