© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15888
    Prev
    Next
    INDEX
    Explanations

    say "sin"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    RESOURCE
    -19.13
    resource
    -18.38
    -resource
    -17.50
     resource
    -17.50
    工程
    -17.38
     RESOURCE
    -17.25
    资源
    -17.25
    施工
    -17.13
    /resource
    -17.00
    _RESOURCE
    -16.75
    POSITIVE LOGITS
     sin
    29.00
    罪
    28.63
    sin
    26.50
    _sin
    25.25
     sins
    25.00
     SIN
    24.13
     Sin
    23.88
    .Sin
    23.25
     sinful
    22.75
    Sin
    22.50
    Activations Density 0.580%

    No Known Activations