© 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. 1993
    Prev
    Next
    INDEX
    Explanations

    => 科技

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

    No Comments

    Negative Logits
    科学
    -43.00
     science
    -41.75
    科技
    -41.50
    科學
    -40.00
     Science
    -38.50
     scientific
    -36.00
    science
    -36.00
    科学技术
    -35.00
    科技创新
    -34.50
     Scientific
    -33.25
    POSITIVE LOGITS
    声音
    18.13
    聲音
    16.00
     Elli
    15.69
    Λ
    15.63
    ье
    14.69
     breathed
    14.63
    Font
    14.13
    ounder
    13.94
     λ
    13.88
     Buckingham
    13.88
    Activations Density 0.076%

    No Known Activations