© 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. 16015
    Prev
    Next
    INDEX
    Explanations

    say "Chinese characters"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    (pg
    -47.75
     PG
    -44.50
    .pg
    -43.50
     pg
    -43.25
     MG
    -43.00
     cg
    -43.00
    IG
    -42.75
     DG
    -42.75
    cg
    -42.50
     SG
    -42.50
    POSITIVE LOGITS
    哆
    15.44
    宙
    15.19
    谶
    14.63
    逦
    14.44
     Levine
    14.44
     Sanford
    14.06
    岙
    14.00
    地坪
    13.88
    谌
    13.88
    Lex
    13.69
    Activations Density 5.895%

    No Known Activations