© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1066
    Prev
    Next
    INDEX
    Explanations

    any => inflammation

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

    No Comments

    Negative Logits
     inflammation
    -41.00
    炎症
    -40.50
     inflammatory
    -33.25
    -inflammatory
    -29.25
    flamm
    -26.88
    flammatory
    -25.88
     inflamm
    -25.13
     innovate
    -24.88
     innovation
    -24.25
    创新
    -24.13
    POSITIVE LOGITS
    字
    20.63
    艺
    17.50
    艺术
    15.50
    教
    14.75
    vector
    14.69
     vector
    14.56
    ライ
    14.19
    教師
    14.13
    码
    13.81
    社
    13.81
    Activations Density 0.081%

    No Known Activations