© 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. 26688
    Prev
    Next
    INDEX
    Explanations

    explaining medical procedures or definitions

    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
    è¿Ļä¹Īåģļ
    -0.09
    è¿Ļæł·åģļ
    -0.09
     theirs
    -0.08
    è¿ĻäºĽå°ı
    -0.07
    bis
    -0.07
    好åij¢
    -0.07
    äºĨè¿Ļä¸Ģ
    -0.07
    è¿Ļ让æĪij
    -0.07
    >:</
    -0.07
    è¿Ļçķª
    -0.07
    POSITIVE LOGITS
    ame
    0.08
     &,
    0.07
    åIJĮä¸Ĭ
    0.07
    !!,
    0.06
    .att
    0.06
    umento
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
     !!
    0.06
    !");
    0.06
    ort
    0.06
    Activations Density 0.088%

    No Known Activations