© 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. 16383
    Prev
    Next
    INDEX
    Explanations

    say "cleaning"

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

    No Comments

    Negative Logits
    元宝
    -19.50
    星座
    -18.88
    腓
    -17.38
     Pyramid
    -17.25
    \Builder
    -17.25
    羿
    -16.88
    lland
    -16.75
    aptor
    -16.63
     Zig
    -15.81
    mars
    -15.81
    POSITIVE LOGITS
    清洁
    53.25
    清洗
    48.75
     cleaning
    48.50
    clean
    48.00
     clean
    47.00
     Clean
    46.75
    Clean
    46.25
     cleaned
    45.25
     cleans
    44.50
    洁净
    44.25
    Activations Density 0.384%

    No Known Activations