© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    diseases and 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
    emaine
    -0.08
    orda
    -0.08
    ç±į
    -0.08
    åľ¨çĽ®
    -0.08
    prost
    -0.08
    西æľį
    -0.08
    éģĵæĿ¥
    -0.07
    PELL
    -0.07
     defaultProps
    -0.07
    anson
    -0.07
    POSITIVE LOGITS
    导èĩ´çļĦ
    0.08
    导èĩ´äºĨ
    0.08
    导èĩ´
    0.07
    åı¯èĥ½å¯¼èĩ´
    0.07
    enburg
    0.07
    æĺ¯å¯¼èĩ´
    0.07
    jej
    0.06
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.06
    èĢĮ导èĩ´
    0.06
    å½±åĵįäºĨ
    0.06
    Activations Density 0.191%

    No Known Activations