© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 529
    Prev
    Next
    INDEX
    Explanations

    say fire

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

    No Comments

    Negative Logits
    薏
    -20.00
    化疗
    -19.50
    乳业
    -19.50
    贵州省
    -19.00
     Fargo
    -19.00
     Illinois
    -19.00
    疟
    -18.50
    溃疡
    -18.13
    墨西哥
    -18.13
     Nebraska
    -18.13
    POSITIVE LOGITS
    火焰
    17.38
     flame
    17.25
     burn
    16.88
    otel
    16.75
    燒
    16.50
    燃烧
    16.38
    aab
    15.94
     Py
    15.56
     burning
    15.44
    (Z
    15.38
    Activations Density 0.050%

    No Known Activations