© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    议

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

    No Comments

    Negative Logits
     Pot
    -17.88
    堇
    -17.13
    _pot
    -17.13
     pot
    -16.75
    -feature
    -16.50
    pot
    -16.13
    -reset
    -15.81
    特征
    -15.50
    机构
    -15.31
     station
    -15.25
    POSITIVE LOGITS
    议
    46.25
    議
    42.00
    议会
    28.63
    议员
    27.63
    议事
    26.50
    议案
    20.88
     nghị
    20.75
    议论
    20.50
    评议
    19.50
    决议
    19.00
    Activations Density 0.058%

    No Known Activations