© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16733
    Prev
    Next
    INDEX
    Explanations

    digits of numbers

    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
    wal
    -0.06
    ÙĪاب
    -0.06
    wizard
    -0.06
    otty
    -0.06
    atria
    -0.06
     [...]
    -0.06
    å¿ħ
    -0.06
    annen
    -0.06
    åºĶçĶ¨ä¸Ń
    -0.05
    æĪIJ
    -0.05
    POSITIVE LOGITS
    ķĮ
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
     thù
    0.08
    edd
    0.08
    yton
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    à¹ģลà¸ģ
    0.07
     disposer
    0.07
     <<<
    0.07
    amet
    0.07
    Activations Density 0.008%

    No Known Activations