© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    say "security"

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

    No Comments

    Negative Logits
    Safety
    -29.13
     Safety
    -28.13
     safety
    -26.50
     safely
    -25.88
     Saf
    -23.88
     Safe
    -22.25
    盐
    -22.25
     safe
    -22.25
    Safe
    -22.25
     SAF
    -22.13
    POSITIVE LOGITS
     security
    26.38
     secure
    24.88
     Security
    24.25
    security
    23.25
    Security
    21.00
    -security
    20.13
     securing
    19.38
     securely
    19.38
     Secure
    18.38
     SECURITY
    18.25
    Activations Density 0.105%

    No Known Activations