© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3290
    Prev
    Next
    INDEX
    Explanations

    say "structure"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    日期
    -15.50
    EventManager
    -15.44
    	event
    -15.38
    <message
    -15.25
    这份
    -15.19
    date
    -14.94
     Cruiser
    -14.94
    eventName
    -14.75
     day
    -14.38
    事件
    -14.38
    POSITIVE LOGITS
     structure
    89.50
     Structure
    82.50
    structure
    81.00
    结构
    80.50
    Structure
    79.50
    _structure
    76.00
     structures
    68.50
    結構
    64.50
    .structure
    61.25
     Structures
    60.00
    Activations Density 0.448%

    No Known Activations