© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    Exodus narrative

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    .cert
    -18.13
     addTarget
    -17.00
    ケット
    -16.50
    录取
    -16.13
    yard
    -16.13
    匡
    -16.00
    内科
    -15.94
     ric
    -15.94
     getSource
    -15.88
    ILT
    -15.81
    POSITIVE LOGITS
     Exodus
    19.25
     Moses
    17.00
     Griff
    16.75
    Ph
    15.81
    埃及
    15.63
    迦
    15.38
     Joshua
    15.25
    牦
    15.06
     Ph
    14.81
    odus
    14.63
    Activations Density 0.215%

    No Known Activations