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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15788
    Prev
    Next
    INDEX
    Explanations

    deep inspiration

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

    No Comments

    Negative Logits
     Skate
    -20.13
     skate
    -20.00
    技术服务
    -18.25
     Suarez
    -16.75
     inputStream
    -16.63
     Sky
    -16.63
    스크
    -16.50
    Sky
    -16.00
    DataService
    -15.88
    膝
    -15.69
    POSITIVE LOGITS
    igner
    16.63
    熏
    16.63
    感悟
    16.63
    (tol
    16.25
    'im
    16.13
     Epstein
    16.13
     emailed
    15.81
    启迪
    15.50
    感受
    15.19
    教育
    15.00
    Activations Density 0.220%

    No Known Activations