© 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. 13914
    Prev
    Next
    INDEX
    Explanations

    say physics

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

    No Comments

    Negative Logits
    调料
    -19.88
     plantation
    -17.75
    AML
    -17.00
    化妆
    -17.00
     UserType
    -16.75
    缓冲
    -16.75
    AuthService
    -16.63
     africa
    -16.63
     AuthService
    -16.38
     targetType
    -16.13
    POSITIVE LOGITS
    物理
    29.13
     physics
    29.13
    物理学
    28.88
     Physics
    27.38
    Physics
    25.63
     physicists
    25.50
     physicist
    24.75
     physical
    23.88
    physics
    23.63
    .physics
    23.00
    Activations Density 0.654%

    No Known Activations