© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1494
    Prev
    Next
    INDEX
    Explanations

    no business

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

    No Comments

    Negative Logits
     business
    -47.25
    Business
    -43.25
     Business
    -43.25
     BUSINESS
    -42.00
    business
    -41.75
    业务
    -40.00
    _business
    -39.00
     Businesses
    -38.25
    /business
    -37.50
     businesses
    -37.00
    POSITIVE LOGITS
    PDF
    14.38
    (pdf
    14.13
    映
    13.56
    焘
    13.56
     eigen
    13.44
     Harry
    13.31
     pdf
    13.25
    -même
    13.19
    Csv
    13.06
     PDF
    13.00
    Activations Density 0.160%

    No Known Activations