© 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. 64267
    Prev
    Next
    INDEX
    Explanations

    health and medical procedures

    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
     sign
    -0.07
    åħ·æľīè¾ĥ强çļĦ
    -0.07
    åıªè¦ģæľī
    -0.07
    ä¸įå¤Ł
    -0.07
    éĥ½æľīäºĨ
    -0.06
    æĮº
    -0.06
     partly
    -0.06
    ä¹Łä¸įä¸Ģå®ļ
    -0.06
     default
    -0.06
    å¾Ī大ä¸Ģéĥ¨åĪĨ
    -0.06
    POSITIVE LOGITS
    严ç¦ģ
    0.20
    åĪĩå¿Į
    0.17
    èĢĮä¸įæĺ¯
    0.16
    åĪĩåĭ¿
    0.16
    ç»Ŀä¸įèĥ½
    0.16
    èĢĮä¸įèĥ½
    0.15
    èĢĮéĿŀ
    0.15
    åįĥä¸ĩä¸įèĥ½
    0.15
    ä¸įåºĶ该
    0.14
    åĪĩè®°
    0.14
    Activations Density 0.177%

    No Known Activations