© 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. 26145
    Prev
    Next
    INDEX
    Explanations

    epidermolysis bullosa

    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
    ä¹Łæĺ¯åįģåĪĨ
    -0.08
    øy
    -0.07
    бÑĥ
    -0.07
     Grosso
    -0.07
    èŀįåĪ¸
    -0.07
    .yahoo
    -0.07
     Sebag
    -0.07
    æĺİæĺ¾æĶ¹åĸĦ
    -0.07
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½æ°ijäºĭè¯ī讼æ³ķ
    -0.07
    æľīä¸Ģå¥Ĺ
    -0.07
    POSITIVE LOGITS
    åŀĭ
    0.12
    åŀĭåĴĮ
    0.11
    åŀĭçļĦ
    0.11
    -Type
    0.10
    ãĤ¿ãĤ¤ãĥĹãģ®
    0.09
    åŀĭãģ®
    0.09
    å¼ı
    0.09
    /type
    0.08
    å¼ıåĴĮ
    0.08
    TYPE
    0.08
    Activations Density 0.665%

    No Known Activations