© 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. 16292
    Prev
    Next
    INDEX
    Explanations

    say stitches

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

    No Comments

    Negative Logits
    ocrates
    -19.13
     Speakers
    -18.88
    _filt
    -18.50
    acam
    -18.50
     дем
    -18.38
     Vulkan
    -18.25
    火山
    -18.13
    curso
    -17.88
    亵
    -17.88
     Filter
    -17.63
    POSITIVE LOGITS
     stitches
    24.63
     threading
    23.13
     stitch
    22.88
    针
    21.75
     stitching
    21.50
     Stitch
    21.38
    针织
    20.75
     threads
    20.25
     thread
    19.63
     needle
    19.63
    Activations Density 0.055%

    No Known Activations