© 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. 57533
    Prev
    Next
    INDEX
    Explanations

    medical history and symptoms

    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
    rach
    -0.06
    åIJĮ声
    -0.06
    çĻĮç»Ĩèĥŀ
    -0.06
    缩
    -0.06
    ville
    -0.06
    ä¼ijçľł
    -0.06
     outgoing
    -0.05
     surplus
    -0.05
     Oscar
    -0.05
    çľ¼å¸ĺ
    -0.05
    POSITIVE LOGITS
    ä¼´æīĭ
    0.10
    æľĪ以æĿ¥
    0.09
    天ä¸ĭ第ä¸Ģ
    0.08
    æĿ¥éĻ¢
    0.08
    è¯ī
    0.08
    มาà¸ģà¹Īà¸Ńà¸Ļ
    0.08
     complains
    0.08
     complaints
    0.08
     мани
    0.08
    Clicked
    0.08
    Activations Density 0.413%

    No Known Activations