© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1084
    Prev
    Next
    INDEX
    Explanations

    say "json"

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

    No Comments

    Negative Logits
     Python
    -20.50
    牛奶
    -19.25
    Python
    -18.50
    骑士
    -17.63
     Sikh
    -17.38
    骑
    -16.63
    骑行
    -16.25
    騎
    -16.13
     Africa
    -16.13
    电话
    -15.50
    POSITIVE LOGITS
    Json
    22.00
     json
    21.50
    json
    21.50
    JSON
    21.38
    -json
    21.25
     Json
    21.13
     JSON
    20.38
     jsonData
    19.75
    /json
    19.38
    云南
    19.00
    Activations Density 0.390%

    No Known Activations