© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3322
    Prev
    Next
    INDEX
    Explanations

    say "digit range"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    configuration
    -19.25
     configuration
    -17.88
    (configuration
    -17.38
    EventType
    -16.75
    浸泡
    -16.25
    =time
    -16.00
     estado
    -15.81
    .configuration
    -15.75
    線
    -15.69
    Configuration
    -15.56
    POSITIVE LOGITS
    关系
    15.06
     Range
    14.69
    Digit
    14.56
    栌
    14.13
    Range
    14.06
    mtree
    13.94
    關係
    13.56
    ldb
    13.00
    kad
    13.00
    ["$
    12.94
    Activations Density 0.009%

    No Known Activations