© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16315
    Prev
    Next
    INDEX
    Explanations

    Cross

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

    No Comments

    Negative Logits
    tron
    -17.13
    (engine
    -17.00
    高位
    -16.75
    工程
    -16.75
     LogManager
    -16.75
    stem
    -16.25
    /engine
    -16.25
    bal
    -16.13
    香菇
    -16.00
     Gauge
    -15.88
    POSITIVE LOGITS
    验证
    18.88
     Borders
    17.25
    культур
    16.88
    AppBundle
    16.63
    注明出处
    15.69
     검
    15.63
     validation
    15.56
     stream
    15.50
    澧
    15.50
    ational
    15.31
    Activations Density 0.014%

    No Known Activations