© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    say "Mer" words

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

    No Comments

    Negative Logits
    uale
    -16.25
    .Ribbon
    -14.81
    UED
    -14.31
    瘗
    -14.19
    uling
    -14.13
    代
    -13.75
    ourse
    -13.31
    进化
    -13.19
    ,pos
    -13.06
    ῦ
    -13.00
    POSITIVE LOGITS
     Mer
    98.50
     mer
    98.00
    Mer
    92.00
    mer
    86.00
     MER
    77.00
    MER
    67.50
     merit
    60.00
    Merit
    57.50
     mercury
    52.50
     Mercury
    49.75
    Activations Density 0.178%

    No Known Activations