© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15494
    Prev
    Next
    INDEX
    Explanations

    capacity building

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

    No Comments

    Negative Logits
    час
    -16.25
    uliar
    -15.94
    壽
    -15.06
     Package
    -14.94
    ackle
    -14.75
    (package
    -14.63
    EXT
    -14.56
    erer
    -14.31
    ulla
    -14.25
    皇后
    -14.06
    POSITIVE LOGITS
    举报电话
    20.50
    培训
    19.25
     training
    19.00
    监管
    18.50
     legal
    17.00
    培训机构
    16.88
    -stock
    16.75
     capacity
    16.75
    -training
    16.63
    _coord
    16.50
    Activations Density 0.312%

    No Known Activations