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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 14063
    Prev
    Next
    INDEX
    Explanations

    say "double"

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

    No Comments

    Negative Logits
    GroupName
    -20.13
    字符
    -19.88
     URLs
    -19.50
    -pages
    -19.00
    字符串
    -18.38
     webs
    -18.00
    网页
    -17.88
     HTML
    -17.75
     URL
    -17.75
    	url
    -17.63
    POSITIVE LOGITS
    double
    23.63
     double
    23.50
    DOUBLE
    22.00
    Double
    21.88
    <Double
    21.63
    _Float
    21.25
    doubleValue
    21.00
    ,double
    20.88
    .double
    20.50
    <double
    20.38
    Activations Density 0.328%

    No Known Activations