© 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. 1735
    Prev
    Next
    INDEX
    Explanations

    [安全] => [安全]

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

    No Comments

    Negative Logits
    安全
    -70.00
     safety
    -60.50
     Safety
    -57.00
    Safety
    -55.25
    的安全
    -55.00
    安全性
    -54.50
    安全保障
    -52.50
     safe
    -49.75
     Safe
    -48.25
     safely
    -48.00
    POSITIVE LOGITS
    ippi
    17.13
    .arch
    16.25
     arch
    16.13
    vation
    15.88
    ARCH
    15.63
    arte
    15.00
     arte
    14.38
     Archer
    14.38
    (GL
    14.06
    -arrow
    14.00
    Activations Density 0.275%

    No Known Activations