© 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. 23267
    Prev
    Next
    INDEX
    Explanations

    axis or road names

    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
    amai
    -0.09
    ç«£
    -0.08
    æݪæīĭä¸įåıĬ
    -0.08
     xá
    -0.08
    ãĤ·ãĥĨãĤ£
    -0.07
    oppi
    -0.07
    lesi
    -0.07
    ìĨ¡
    -0.07
    Defaults
    -0.07
    å±Ĥåĩºä¸įç©·
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸ĢæĿ¡
    0.08
    idian
    0.08
    ä¸Ń央
    0.07
    å¼Ħ
    0.07
    æĹłå°ĺ
    0.07
    å¼ģ
    0.07
    é¦ĸ
    0.06
     central
    0.06
    æĪ·æĻĵ
    0.06
    æĸ¹åIJij
    0.06
    Activations Density 0.014%

    No Known Activations