© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    say technology

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

    No Comments

    Negative Logits
     металл
    -15.44
    变量
    -15.38
    算了
    -15.13
     Band
    -14.94
    .band
    -14.81
     Arizona
    -14.50
     statically
    -14.38
    .Setter
    -14.25
    甘肃省
    -14.13
    Band
    -14.00
    POSITIVE LOGITS
    技术创新
    24.13
    科技创新
    22.63
     innovate
    20.75
     TECHNO
    19.75
     technology
    19.75
    科技
    19.75
    Technology
    19.25
     Technology
    18.88
    Liter
    18.75
    科技进步
    18.63
    Activations Density 0.269%

    No Known Activations