© 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. 3339
    Prev
    Next
    INDEX
    Explanations

    dates

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     system
    -21.13
    系统
    -19.25
    系統
    -18.50
    模型
    -18.25
    	system
    -18.13
    系统的
    -17.75
     System
    -17.63
    system
    -17.25
    System
    -17.13
    (system
    -17.13
    POSITIVE LOGITS
     December
    28.13
    日
    27.50
     February
    27.50
     November
    26.75
     October
    26.50
    日期
    26.50
     January
    25.75
     September
    24.88
     date
    24.88
     April
    24.75
    Activations Density 0.113%

    No Known Activations