© 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. 43785
    Prev
    Next
    INDEX
    Explanations

    methylene blue photoinactivation

    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
    åŃ°
    -0.07
    åĴĮ责任
    -0.07
    ä¸įèĥ½è¯´
    -0.06
    å¿ĺäºĨ
    -0.06
    inig
    -0.06
    ÙĪØ®
    -0.06
    yg
    -0.06
     subject
    -0.06
     benefiting
    -0.06
    æĥłåıĬ
    -0.06
    POSITIVE LOGITS
    ä½ľçĤº
    0.09
    ä½ľä¸ºä¸Ģç§į
    0.09
    åģļ为
    0.08
    raph
    0.08
    çĶ¨ä½ľ
    0.08
     ìŀIJì²´ê°Ģ
    0.08
    ç´łæľī
    0.08
    åħ·æľīè¾ĥ强çļĦ
    0.08
    çļĦ强大
    0.08
    ä½ľä¸º
    0.07
    Activations Density 0.017%

    No Known Activations