© 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. 7585
    Prev
    Next
    INDEX
    Explanations

    health and medical studies

    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
    eggio
    -0.07
    éĿ¡
    -0.07
    urt
    -0.07
    å·¥ä¸ļåĩºçīĪ社
    -0.07
    regs
    -0.07
    ìłģìĿ´ê³ł
    -0.07
    áf
    -0.06
    åĴĮæľīåħ³
    -0.06
    agaan
    -0.06
    æĥ³è¯´
    -0.06
    POSITIVE LOGITS
    两ä¸į误
    0.07
    çŁ¥ä¹ĭ
    0.07
    ãģ¨ãģĦãģ£ãģŁ
    0.07
    atique
    0.06
    oters
    0.06
    çŃīçī¹çĤ¹
    0.06
    ä¹ĭ交
    0.06
    ohan
    0.06
    ÑĨио
    0.06
    æķĻåŃ¦è®¡åĪĴ
    0.06
    Activations Density 0.119%

    No Known Activations