© 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. 563
    Prev
    Next
    INDEX
    Explanations

    say "Linux"

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

    No Comments

    Negative Logits
    昆
    -20.00
     Draco
    -19.63
    琼
    -19.38
    唐山
    -18.63
     Naruto
    -18.38
     Orioles
    -17.88
    滹
    -17.88
     McD
    -17.88
     Хо
    -17.75
     Airways
    -17.50
    POSITIVE LOGITS
     Linux
    58.75
    Linux
    57.50
     linux
    52.00
    linux
    48.25
     LINUX
    47.75
    _linux
    46.50
    /linux
    45.25
    /Linux
    44.50
    -linux
    43.50
    Ubuntu
    41.50
    Activations Density 0.114%

    No Known Activations