© 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. 3024
    Prev
    Next
    INDEX
    Explanations

    say "治"

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

    No Comments

    Negative Logits
    ’
    -18.63
    径
    -17.13
    ð
    -17.00
    _idx
    -17.00
    徑
    -16.88
     �
    -16.75
    乙方
    -16.75
     Reservation
    -16.75
    semantic
    -16.25
    _RET
    -16.13
    POSITIVE LOGITS
    治
    57.50
    治好
    34.25
     treatment
    29.13
    治理
    28.00
     treatments
    26.25
    治疗
    26.13
    防治
    25.75
     Treatment
    24.88
     treat
    24.00
     therapy
    23.88
    Activations Density 0.086%

    No Known Activations