© 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. 13888
    Prev
    Next
    INDEX
    Explanations

    adverse medical conditions and procedures

    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
    ä¹Łä¸įæĢķ
    -0.08
    åħĭ森
    -0.08
    èĥ½ä»¥
    -0.07
    _patches
    -0.07
    ildo
    -0.07
    åIJĥ好
    -0.07
    秽
    -0.06
     luckily
    -0.06
    è¿Ļæł·å°±åı¯ä»¥
    -0.06
    .cal
    -0.06
    POSITIVE LOGITS
     improperly
    0.12
     inadvertently
    0.11
     ÑģлиÑĪком
    0.09
    ä¸įæħİ
    0.09
    cessive
    0.09
     excessively
    0.09
    ä¸įå½ĵ
    0.09
     unnecessarily
    0.09
     pÅĻÃŃliÅ¡
    0.09
    ä¸įå¾Ĺå·²
    0.09
    Activations Density 0.812%

    No Known Activations