© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1987
    Prev
    Next
    INDEX
    Explanations

    non‑language words

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

    No Comments

    Negative Logits
    语
    -34.75
    语言
    -34.25
    語
    -31.50
    語言
    -29.00
     language
    -28.75
    的语言
    -28.63
     Language
    -25.38
     languages
    -24.00
    Language
    -23.75
     Languages
    -23.00
    POSITIVE LOGITS
    咖啡
    17.00
    logging
    15.56
    茶园
    15.38
    コーヒー
    15.31
    油烟
    15.19
    纤维
    14.75
    .Logging
    14.50
     logs
    14.50
    光纤
    14.38
    shall
    14.13
    Activations Density 0.059%

    No Known Activations