© 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. 17160
    Prev
    Next
    INDEX
    Explanations

    fetal medical conditions

    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
    å¤ĦçIJĨåIJİ
    -0.08
    æŃĩ
    -0.08
    éĹ²ç½®
    -0.08
    纯åĮĸ
    -0.07
    çķ´
    -0.07
    æĪĺåIJİ
    -0.07
    ä¸ļåĬ¡å·¥ä½ľ
    -0.07
    Atomic
    -0.07
    Autom
    -0.07
    istra
    -0.07
    POSITIVE LOGITS
    èĥİ
    0.13
    èĥİåĦ¿
    0.11
     fetal
    0.11
     fetus
    0.10
    å®Ŀå®ĿçļĦ
    0.09
    宫åĨħ
    0.09
     unborn
    0.09
    åŃķ
    0.09
    ç¾Ĭæ°´
    0.09
    åĩºçĶŁåIJİ
    0.09
    Activations Density 0.057%

    No Known Activations