© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    say safety

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

    No Comments

    Negative Logits
    罗马
    -34.25
     Roman
    -33.00
     Romans
    -31.13
     Rome
    -31.00
    Roman
    -28.13
     roman
    -27.13
    roman
    -24.75
    汉
    -23.75
     Roma
    -23.63
    漢
    -22.50
    POSITIVE LOGITS
     safety
    16.88
     safe
    16.25
     Safety
    15.56
     QLD
    15.25
    在深圳
    15.13
    翼
    15.00
    安全
    14.81
     safely
    14.56
     KING
    14.44
    Safety
    14.38
    Activations Density 0.110%

    No Known Activations