© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    national health expenditures

    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
    à§įষ
    -0.08
     terlebih
    -0.07
    alla
    -0.07
     eerst
    -0.07
    ãģ¨ãģĹãģ¦ãģ¯
    -0.07
    vg
    -0.07
    emar
    -0.07
    åīįæľŁ
    -0.07
    å°¼å°Ķ
    -0.06
    ãģ¾ãģļãģ¯
    -0.06
    POSITIVE LOGITS
    æŃ£å¼ıçļĦ
    0.08
    å°±æĺ¯æĪijçļĦ
    0.08
    è¿ĶåĽŀ顶éĥ¨
    0.08
    ÏĢει
    0.08
    rok
    0.08
    æĹ¥æŃ£å¼ı
    0.08
     formally
    0.07
    -sama
    0.07
    æŃ£å¼ı
    0.07
    个çľģ
    0.07
    Activations Density 0.001%

    No Known Activations