© 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. 974
    Prev
    Next
    INDEX
    Explanations

    say ca

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Seoul
    -21.75
    韓
    -19.75
     Korean
    -18.75
    是韩国
    -18.75
    韩
    -18.00
    韩国
    -18.00
    覃
    -17.75
    荔
    -17.00
    朝鲜
    -17.00
     Lee
    -16.75
    POSITIVE LOGITS
     CA
    81.50
    CA
    76.50
     ca
    68.50
    _CA
    67.50
     Ca
    67.50
    (ca
    66.50
    Ca
    65.00
    _ca
    63.75
    /ca
    63.25
    曹
    61.75
    Activations Density 0.224%

    No Known Activations