© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14914
    Prev
    Next
    INDEX
    Explanations

    say "type"

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

    No Comments

    Negative Logits
    编码
    -18.75
     gridSize
    -18.13
    探测
    -17.63
    氦
    -17.25
    getField
    -17.25
    酗
    -17.00
    编程
    -16.88
    工程项目
    -16.88
    (grid
    -16.75
     输出
    -16.38
    POSITIVE LOGITS
     type
    17.00
    .TYPE
    16.13
     kind
    15.06
    <![
    14.69
     types
    14.69
    type
    13.50
    aly
    13.50
     lakh
    13.06
     option
    12.81
    .Type
    12.81
    Activations Density 0.145%

    No Known Activations