© 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. 61884
    Prev
    Next
    INDEX
    Explanations

    mathematical variable expressions

    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
    å·¦ä¸Ĭ
    -0.07
    被æµĭ
    -0.06
    水泡
    -0.06
    enti
    -0.06
    ocre
    -0.06
     enlarge
    -0.06
    endom
    -0.06
    åıĮåıĮ
    -0.06
    磨
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
    θή
    0.07
    ellik
    0.07
    å¿Ĺ
    0.07
    ঢ
    0.07
    åįķä½įåĴĮ个人
    0.07
    اÙĨÙĩ
    0.07
    rata
    0.07
    æݨ
    0.07
    razil
    0.06
    arkin
    0.06
    Activations Density 0.017%

    No Known Activations