© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14680
    Prev
    Next
    INDEX
    Explanations

    say 5

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

    No Comments

    Negative Logits
     alf
    -19.50
    杯
    -18.75
     Citadel
    -18.25
    Twig
    -17.63
    .twig
    -17.63
    梧
    -17.50
     Gaul
    -17.50
     stringBuffer
    -17.38
    =top
    -17.38
     Tik
    -17.25
    POSITIVE LOGITS
    三十
    17.25
    finite
    16.63
     Jan
    15.31
    Jan
    15.25
    跖
    14.75
    屦
    14.31
    一脚
    14.25
    三十年
    13.63
     Ply
    13.56
    연
    13.44
    Activations Density 0.120%

    No Known Activations