© 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. 15248
    Prev
    Next
    INDEX
    Explanations

    say "mar" words

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

    No Comments

    Negative Logits
    hlen
    -15.75
     skl
    -15.63
    .cv
    -15.31
    电气
    -15.31
    /orders
    -15.13
    /licenses
    -14.94
    igue
    -14.56
    ationToken
    -14.38
    usters
    -14.19
    etrain
    -14.19
    POSITIVE LOGITS
     mar
    46.00
     MAR
    45.25
    mar
    45.25
    Mar
    42.75
    _mar
    41.75
    .mar
    41.25
     Mar
    40.75
    .Mar
    40.75
    MAR
    40.50
    -mar
    40.25
    Activations Density 0.163%

    No Known Activations