© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15849
    Prev
    Next
    INDEX
    Explanations

    compression

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

    No Comments

    Negative Logits
    民办
    -17.75
    aturity
    -17.13
    捐助
    -16.50
     roleId
    -15.88
    urved
    -15.63
    �单
    -15.63
     Evel
    -15.56
    roleId
    -15.50
    ectl
    -15.44
    .DrawLine
    -15.44
    POSITIVE LOGITS
    压缩
    49.50
     compression
    48.50
     compress
    44.75
     compressed
    44.75
     Compression
    44.25
    compression
    43.75
    compress
    43.25
    compressed
    43.00
    Compression
    43.00
     compressor
    39.25
    Activations Density 0.093%

    No Known Activations