© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    inflation

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

    No Comments

    Negative Logits
    炎症
    -31.63
     inflammation
    -31.00
     innovation
    -30.75
     Innovation
    -30.13
    创新
    -29.38
     innovate
    -28.88
     innovations
    -26.75
     inflammatory
    -26.00
     innovative
    -25.50
    創新
    -25.50
    POSITIVE LOGITS
     Arts
    19.75
    艺
    18.00
     Arthur
    18.00
     art
    17.63
    艺术
    17.38
     arts
    17.00
    Art
    16.75
    .Art
    16.75
     Art
    16.25
     искусств
    16.25
    Activations Density 0.042%

    No Known Activations