© 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. 32861
    Prev
    Next
    INDEX
    Explanations

    tumors and diseases ending in -oma, -osis, -itis

    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
    çļĦæŶåĢĻäºĨ
    -0.08
    гей
    -0.08
    诽谤
    -0.07
    geme
    -0.07
    agnes
    -0.07
    æľįåĬ¡çŃī
    -0.07
    agan
    -0.07
     окажеÑĤÑģÑı
    -0.07
    ä¸ŃäºĨ
    -0.07
    apper
    -0.07
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.10
    æĺ¯ä¸Ģç§įéĿŀ常
    0.08
    ìĿ´ëŀĢ
    0.08
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.08
    è¿Ļ个è¯į
    0.08
    åıĪ称
    0.08
    æĺ¯æĮĩåľ¨
    0.07
    æĺ¯ä¸Ģç§į
    0.07
    å®ĥæĺ¯ä¸Ģç§į
    0.07
    æĺ¯ä¸Ģ个éĿŀ常
    0.07
    Activations Density 0.337%

    No Known Activations