© 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. 43116
    Prev
    Next
    INDEX
    Explanations

    medical conditions and health effects

    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
    èıģ
    -0.09
    Ñĥбли
    -0.08
    家æĺ¯
    -0.08
    idik
    -0.07
    åĪĩå®ŀå¢ŀ强
    -0.07
    ìŀ¡
    -0.07
    gaard
    -0.07
    APPED
    -0.07
    ális
    -0.07
     unknown
    -0.07
    POSITIVE LOGITS
    éĹ´æİ¥
    0.12
     indirect
    0.10
     indirectly
    0.10
     indire
    0.10
    ä»İèĢĮ
    0.09
    ä»İèĢĮå½±åĵį
    0.08
     thereby
    0.08
    ä»İèĢĮ导èĩ´
    0.08
    аÑĢи
    0.07
     Via
    0.07
    Activations Density 0.145%

    No Known Activations