© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1131
    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
    墨
    -39.75
    水墨
    -25.38
     Musk
    -22.50
    psi
    -18.88
     Heath
    -18.75
     Vide
    -18.25
    筝
    -18.00
    翰
    -17.75
     Morse
    -17.63
     MSR
    -17.63
    POSITIVE LOGITS
    安全
    23.88
    安全管理
    22.63
    的安全
    21.13
    安全保障
    20.63
     Sicher
    20.63
     SAF
    20.50
     safety
    20.38
    安全事故
    20.25
    宗教
    19.63
    Safety
    19.25
    Activations Density 0.051%

    No Known Activations