© 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. 14264
    Prev
    Next
    INDEX
    Explanations

    say pattern

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

    No Comments

    Negative Logits
    活動
    -17.88
     setContent
    -16.88
    CTS
    -16.63
    活动中
    -16.63
    setQuery
    -16.63
    Activity
    -16.50
     activity
    -16.38
    痿
    -16.25
    activities
    -16.13
    setContent
    -16.13
    POSITIVE LOGITS
     pattern
    33.00
     Pattern
    31.75
    pattern
    30.63
    _pattern
    29.75
     patterns
    29.75
    Pattern
    29.13
    纹
    28.38
    图案
    26.88
    _PATTERN
    26.38
     Patterns
    26.25
    Activations Density 0.364%

    No Known Activations