© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9080
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħĪ
    -0.08
    è¿
    -0.07
    zeh
    -0.07
    ç»İ
    -0.07
    èĤĺ
    -0.06
    æĪijåĴĮæĪijçļĦ
    -0.06
    éĩijæĸ¯
    -0.06
    æŃ£å¼ı
    -0.06
    stit
    -0.06
    åĬ
    -0.06
    POSITIVE LOGITS
    人æĹł
    0.08
    讲åĪ°
    0.08
    ä¸ĵ家æĮĩåĩº
    0.08
     Ñĥпо
    0.08
    ãģ«æĪ»ãĤĭ
    0.07
    åŁ¹ä¼ĺ
    0.07
    è¿Ļ让æĪij
    0.07
    ä¹ĭä¸Ģæĺ¯
    0.07
     gợi
    0.07
     suficiente
    0.07
    Activations Density 0.006%

    No Known Activations