© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    Method 2 – all TOKENS_AFTER_MAX_ACTIVATING_TOKEN are single‑digit numbers. say digits

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    -file
    -22.38
    文件
    -22.00
     file
    -21.25
    =file
    -21.13
    FILE
    -20.75
    file
    -20.75
    	file
    -20.75
    _file
    -20.50
     FILE
    -20.50
     файла
    -19.88
    POSITIVE LOGITS
    方向
    20.38
    类型
    20.38
    元素
    20.13
     type
    19.63
     direction
    18.25
     Type
    18.13
     elementType
    17.75
     elements
    17.75
    Type
    16.75
    发展方向
    16.38
    Activations Density 0.687%

    No Known Activations