© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    say "退"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    镜
    -20.25
    Rep
    -19.00
     rep
    -18.63
     net
    -18.25
    Net
    -17.75
     mirrors
    -17.25
     poly
    -17.13
    情感
    -16.88
    鏡
    -16.75
     morph
    -16.63
    POSITIVE LOGITS
    (ret
    46.50
    Ret
    45.25
    ret
    45.00
    .ret
    43.75
     ret
    43.50
     Ret
    43.00
    -ret
    40.50
     RET
    39.50
    退
    39.50
    _ret
    39.25
    Activations Density 0.082%

    No Known Activations