© 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. 15692
    Prev
    Next
    INDEX
    Explanations

    say emergency

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

    No Comments

    Negative Logits
    _CSS
    -19.13
    宫殿
    -18.50
     Knight
    -17.00
     extraction
    -16.13
     ffmpeg
    -16.00
    -css
    -16.00
    lng
    -15.75
     Extraction
    -15.63
    Sdk
    -15.63
     Garc
    -15.63
    POSITIVE LOGITS
    暴
    17.38
    控制
    16.88
    爆
    16.63
    曲线
    16.00
    agues
    16.00
    aida
    16.00
    危机
    15.94
    curve
    15.88
     spread
    15.75
    Control
    15.56
    Activations Density 0.154%

    No Known Activations