© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15173
    Prev
    Next
    INDEX
    Explanations

    [&] => [Drug]

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

    No Comments

    Negative Logits
     poll
    -20.63
    .capture
    -19.13
    capture
    -18.50
    硅谷
    -17.25
    projection
    -17.25
    _traits
    -17.13
    捕捉
    -17.13
    poll
    -17.00
     polling
    -16.88
     bytesRead
    -16.88
    POSITIVE LOGITS
     Standards
    16.63
    angu
    15.31
     pages
    13.94
     safety
    13.88
     standards
    13.81
    df
    13.63
    pages
    13.63
    安全
    13.50
     listings
    13.31
    Safety
    13.31
    Activations Density 0.003%

    No Known Activations