© 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. 16077
    Prev
    Next
    INDEX
    Explanations

    [political] => [economic]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     pol
    -19.75
    -digit
    -18.75
     trous
    -18.75
     mật
    -17.75
     Digit
    -17.63
    _pol
    -17.38
    Pol
    -17.38
     digit
    -17.38
     Pol
    -16.63
    izen
    -16.63
    POSITIVE LOGITS
    表达
    18.25
    表达了
    16.00
    .SDK
    15.69
     đám
    15.50
    格局
    15.44
    华尔
    15.31
    /context
    15.06
    elta
    15.00
    保护
    14.88
     expression
    14.81
    Activations Density 0.075%

    No Known Activations