© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    technology

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

    No Comments

    Negative Logits
     pen
    -17.13
    蜩
    -16.25
    册
    -16.00
     Pen
    -15.50
     Pens
    -14.69
    zem
    -14.63
     CAP
    -14.50
    Pen
    -14.38
    mland
    -14.38
    =item
    -14.25
    POSITIVE LOGITS
    科技
    85.50
     tech
    66.00
     Tech
    61.50
    tech
    58.50
    科技创新
    58.00
    Tech
    56.75
     technology
    56.50
    科技成果
    54.75
     Technology
    53.25
     technological
    52.75
    Activations Density 0.200%

    No Known Activations