© 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. 1606
    Prev
    Next
    INDEX
    Explanations

    say single-letter

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

    No Comments

    Negative Logits
     logging
    -37.50
    逻辑
    -37.25
    Log
    -34.75
    Logging
    -34.25
     logarith
    -34.00
     Log
    -34.00
     LOG
    -33.75
    灯
    -33.75
     logic
    -33.25
    logging
    -33.25
    POSITIVE LOGITS
    OOM
    18.50
     Motorola
    16.75
    oric
    13.81
    IRD
    13.25
    .med
    12.94
    .GO
    12.94
    tesy
    12.88
    嵯
    12.75
    игра
    12.56
    Python
    12.25
    Activations Density 0.622%

    No Known Activations