© 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. 1760
    Prev
    Next
    INDEX
    Explanations

    physical descriptors

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

    No Comments

    Negative Logits
    物理
    -54.00
     physics
    -51.00
     Physics
    -48.00
    物理学
    -47.75
    Physics
    -45.75
    physics
    -45.25
     PHYS
    -43.25
     physic
    -43.00
     física
    -41.00
    phys
    -40.00
    POSITIVE LOGITS
     Britann
    16.25
     السعودي
    15.13
     Arabia
    15.13
     axios
    14.00
    深交所
    13.44
     Axios
    13.25
    算法
    13.00
    VIDEO
    12.88
     Jordan
    12.75
     Yam
    12.63
    Activations Density 0.108%

    No Known Activations