© 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. 1832
    Prev
    Next
    INDEX
    Explanations

    do not say legal

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

    No Comments

    Negative Logits
    依法
    -38.50
    法律
    -32.75
     legal
    -31.25
     legally
    -30.50
     legality
    -30.13
    Legal
    -29.25
    合法
    -29.13
     law
    -28.38
    法律法规
    -27.63
    legal
    -27.13
    POSITIVE LOGITS
     CARD
    16.38
     cardinal
    16.00
    Shopping
    15.06
     numeral
    15.06
    socket
    14.69
    鱿
    14.56
    theid
    14.38
    -card
    14.00
    文学
    14.00
     Kart
    13.94
    Activations Density 0.067%

    No Known Activations