© 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. 20892
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions and concepts

    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
    ugs
    -0.07
    Ø´ÙĨ
    -0.06
    ar
    -0.06
    ä»İä¸Ń
    -0.06
    aque
    -0.06
    arrow
    -0.06
    ÏĦÏģο
    -0.06
    arp
    -0.06
     D
    -0.05
    upe
    -0.05
    POSITIVE LOGITS
    åīįèĢħ
    0.10
    à¹ģà¸ķà¹Īละ
    0.10
     каждого
    0.09
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    0.09
     masing
    0.08
    æ¯ı项
    0.08
     каждой
    0.08
     обоиÑħ
    0.08
    æ¯ıç§į
    0.08
    à¸Ĥà¸Ńà¸ĩà¹ģà¸ķà¹Īละ
    0.08
    Activations Density 0.217%

    No Known Activations