© 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. 33114
    Prev
    Next
    INDEX
    Explanations

    including applications development

    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
    ä»Ģä¹Īåij¢
    -0.08
    æĪijæľĢåĸľæ¬¢
    -0.07
     Shutterstock
    -0.07
     almost
    -0.07
    æīĢåľ¨åľ°åĮº
    -0.07
    æīĢè°ĵçļĦ
    -0.07
     bezieh
    -0.07
    èĤ²
    -0.07
    æĪijåĴĮæĪijçļĦ
    -0.07
    ucht
    -0.07
    POSITIVE LOGITS
    为éĩįçĤ¹
    0.07
    ÙĨÙĬÙĩ
    0.06
    ¨
    0.06
     emphas
    0.06
    åĪĨå±Ģ
    0.06
    强è°ĥ
    0.06
    ç®ĹäºĨ
    0.06
     dangers
    0.06
    פ×Ķ
    0.06
    ÑħнÑĥÑĤÑĮ
    0.06
    Activations Density 0.004%

    No Known Activations