© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15007
    Prev
    Next
    INDEX
    Explanations

    say "mercury"

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

    No Comments

    Negative Logits
    南沙
    -17.13
    cci
    -16.88
    艺术品
    -16.75
     Palm
    -16.63
    腳
    -16.38
     Sands
    -16.00
     SAND
    -16.00
     Crafts
    -16.00
     Nolan
    -15.81
    caffold
    -15.75
    POSITIVE LOGITS
    汞
    24.88
     mercury
    19.25
    mer
    17.88
     mer
    16.50
    液
    16.38
     Mercury
    15.75
     MER
    15.56
    MER
    15.50
     waterfall
    14.56
     mercy
    13.94
    Activations Density 0.074%

    No Known Activations