© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    say "excellence"

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

    No Comments

    Negative Logits
     renov
    -17.88
    分彩
    -17.75
     Qin
    -16.50
     Ying
    -16.25
     Feng
    -16.25
     Mandarin
    -16.13
     Nguyễn
    -16.13
    奶茶
    -15.81
     bếp
    -15.63
     buffet
    -15.13
    POSITIVE LOGITS
    卓越
    17.25
    卓
    17.00
    .IM
    17.00
    世界级
    16.38
    非凡
    16.25
    目标
    16.13
    ål
    15.94
     mund
    15.75
    杰出
    15.75
     dreamed
    15.44
    Activations Density 0.460%

    No Known Activations