© 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. 3200
    Prev
    Next
    INDEX
    Explanations

    say "target"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     groups
    -17.50
    line
    -15.94
    groups
    -15.31
     group
    -14.81
    的过程
    -14.50
    $body
    -14.38
     grouping
    -14.31
     environment
    -14.31
    omencl
    -14.31
     line
    -14.25
    POSITIVE LOGITS
    target
    20.13
     target
    19.88
    [target
    18.75
    _target
    18.63
    (target
    18.00
    冷藏
    17.13
    Treatment
    17.00
     gigg
    16.88
    .source
    16.88
    .target
    16.88
    Activations Density 0.005%

    No Known Activations