© 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. 2187
    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
    uling
    -17.75
    (sim
    -16.25
     sims
    -15.81
    千元
    -15.63
     SIM
    -15.56
    啃
    -15.50
    ingly
    -15.19
    quee
    -15.13
    .Ribbon
    -15.06
    ildo
    -14.81
    POSITIVE LOGITS
    Mer
    71.00
     mer
    68.50
     Mer
    68.00
     mercury
    67.00
    mer
    65.00
     Mercury
    62.75
     MER
    57.75
    汞
    52.25
    MER
    48.25
     Merc
    43.00
    Activations Density 0.066%

    No Known Activations