© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    Chinese moral concepts

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Pumpkin
    -18.25
     Skull
    -17.38
    .Stream
    -17.25
    火箭
    -16.88
    秃
    -16.88
     skateboard
    -16.50
    飞船
    -16.38
     helicopters
    -16.25
     Boat
    -16.25
     helicopter
    -16.25
    POSITIVE LOGITS
    德
    18.75
    uje
    17.38
    _ur
    16.50
    že
    16.38
    rix
    16.25
    .ur
    16.13
     ux
    16.13
    範
    16.00
    庶
    15.94
     nic
    15.75
    Activations Density 0.265%

    No Known Activations