© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13950
    Prev
    Next
    INDEX
    Explanations

    say privacy

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

    No Comments

    Negative Logits
    考场
    -21.25
    分彩
    -19.75
    锦标
    -18.00
    考点
    -17.25
    Fizz
    -17.00
    fixture
    -17.00
    시험
    -16.63
     staging
    -16.50
    -devel
    -16.38
    外国语
    -16.38
    POSITIVE LOGITS
     privacy
    36.00
    隐私
    33.00
     Privacy
    32.75
    Privacy
    31.63
    个人信息
    31.13
     PRIV
    30.00
     personal
    29.63
    privacy
    29.38
    和个人
    29.38
    个人
    29.00
    Activations Density 0.426%

    No Known Activations