© 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. 14755
    Prev
    Next
    INDEX
    Explanations

    say "law"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    δ
    -16.38
     Beit
    -15.69
     Schwartz
    -15.06
     δ
    -15.00
    睫
    -14.88
     Bayesian
    -14.75
    ül
    -14.25
    onitor
    -14.19
    楼
    -14.19
    ListGroup
    -14.06
    POSITIVE LOGITS
    law
    18.25
     rider
    18.13
     riders
    17.50
    laws
    17.38
     Riders
    17.00
     Law
    16.88
    kills
    16.75
     law
    16.63
     LAW
    16.63
    Law
    16.38
    Activations Density 0.235%

    No Known Activations