© 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. 16607
    Prev
    Next
    INDEX
    Explanations

    smallest or biggest value

    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
    ļĮ
    -0.08
    adlo
    -0.08
    awn
    -0.07
    åıĮ缮
    -0.07
    etz
    -0.07
    upe
    -0.07
    宿
    -0.07
    éĢĢä¼ijéĩij
    -0.07
    rets
    -0.07
    /io
    -0.07
    POSITIVE LOGITS
    æİĴåºı
    0.13
     sorted
    0.11
    _sorted
    0.11
     Sorted
    0.10
    ä»İå°ıåĪ°å¤§
    0.09
    sorted
    0.09
    Sorted
    0.09
    à¹Ģรียà¸ĩ
    0.09
    -ranked
    0.09
     sorting
    0.09
    Activations Density 0.006%

    No Known Activations