© 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. 978
    Prev
    Next
    INDEX
    Explanations

    say "Microsoft"

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

    No Comments

    Negative Logits
    烬
    -18.50
    烟花
    -17.13
    /boot
    -17.13
     FreeBSD
    -16.75
    SSH
    -16.63
    笋
    -16.63
    .pathname
    -16.38
     Carn
    -16.38
     Penal
    -16.38
     Tropical
    -16.25
    POSITIVE LOGITS
    微软
    26.38
     Microsoft
    25.88
    Microsoft
    25.75
    icrosoft
    21.50
     Office
    20.88
    .Microsoft
    20.63
    Office
    20.38
     microsoft
    19.00
    _office
    19.00
    Px
    18.63
    Activations Density 0.057%

    No Known Activations