© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1354
    Prev
    Next
    INDEX
    Explanations

    New England towns

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

    No Comments

    Negative Logits
     Massachusetts
    -29.00
     Boston
    -27.25
    Boston
    -26.63
    福建
    -19.88
     Brigham
    -18.63
    福建省
    -18.50
     Suffolk
    -17.75
    哈佛
    -17.50
     apple
    -17.13
     Harvard
    -17.00
    POSITIVE LOGITS
    潢
    18.00
    -google
    16.63
    秧
    16.50
    _ui
    15.63
    Spy
    15.50
    电脑
    15.50
    Windows
    15.44
    uales
    14.88
    豪车
    14.88
    -photo
    14.81
    Activations Density 0.171%

    No Known Activations