© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15746
    Prev
    Next
    INDEX
    Explanations

    say "工"

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

    No Comments

    Negative Logits
    erview
    -16.50
    ALLOC
    -16.25
    走访
    -16.13
    Vis
    -16.13
    Alan
    -16.00
    -Al
    -15.88
    &view
    -15.50
    Al
    -15.38
     airflow
    -15.31
    通风
    -15.31
    POSITIVE LOGITS
     Crush
    23.38
    结晶
    23.13
    水晶
    23.00
     crushing
    22.00
     crystall
    22.00
    .cr
    21.25
    cr
    20.63
     crystal
    20.13
    宝石
    20.13
     cruc
    19.13
    Activations Density 0.229%

    No Known Activations