© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14120
    Prev
    Next
    INDEX
    Explanations

    say "api"

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

    No Comments

    Negative Logits
    条件
    -18.25
    лев
    -16.75
    .swing
    -16.63
    耧
    -16.50
    /licenses
    -16.13
    描写
    -16.13
     Sudoku
    -16.00
    进球
    -15.81
    CONDITION
    -15.75
    entr
    -15.63
    POSITIVE LOGITS
     api
    34.00
     API
    33.75
     Api
    33.25
     getRequest
    32.75
     request
    32.75
    api
    32.25
    API
    32.25
    请求
    32.00
     requests
    31.88
     APIs
    31.25
    Activations Density 0.650%

    No Known Activations