© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    poverty

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Po
    -37.25
     Po
    -35.00
     PO
    -34.25
    -po
    -34.00
     poetry
    -34.00
    _po
    -33.50
    诗
    -33.50
     poverty
    -33.25
     Poetry
    -32.25
    詩
    -32.25
    POSITIVE LOGITS
     Europe
    15.56
    ych
    15.44
     gui
    15.38
    éd
    15.19
    _widgets
    15.06
    游戏
    14.94
     Switch
    14.81
     Game
    14.69
     games
    14.69
     European
    14.38
    Activations Density 0.075%

    No Known Activations