© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    say engine

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     moon
    -41.25
     Moon
    -40.50
    Moon
    -37.25
    月亮
    -36.50
    月
    -35.00
    moon
    -31.75
     lunar
    -30.00
    月下
    -27.38
     moons
    -27.13
    月至
    -27.00
    POSITIVE LOGITS
     Fabric
    18.38
    Fabric
    17.50
     engineered
    17.50
    ക
    17.25
    engine
    17.25
     Ballard
    16.88
    _ENGINE
    16.75
    -engine
    16.63
    Engine
    16.50
    ENGINE
    16.25
    Activations Density 0.087%

    No Known Activations