© 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. 16832
    Prev
    Next
    INDEX
    Explanations

    jsfiddle or github links

    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
    eden
    -0.08
    hir
    -0.07
    hill
    -0.07
    ার
    -0.07
    raq
    -0.07
    ailed
    -0.07
    é»ijæ´ŀ
    -0.07
    oney
    -0.07
    verd
    -0.07
    moil
    -0.06
    POSITIVE LOGITS
     (!((
    0.07
    èĢĮæľª
    0.07
    æĪIJåIJį
    0.07
    wnd
    0.07
    æª
    0.07
    æ¬
    0.07
    幡
    0.06
    ×Ĺ×Ļ
    0.06
    ieÃŁ
    0.06
    槻
    0.06
    Activations Density 0.001%

    No Known Activations