© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44263
    Prev
    Next
    INDEX
    Explanations

    scientific expression

    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
    Negative Logits
    باش
    -0.08
    ience
    -0.08
    çļĦ
    -0.07
    Ñĭн
    -0.07
     lá»Ļi
    -0.07
    craft
    -0.07
    ilt
    -0.07
    èĴĻå¾·
    -0.07
    itudes
    -0.07
    ilitation
    -0.07
    POSITIVE LOGITS
    Ø©
    0.09
    sweise
    0.08
     involving
    0.07
    halb
    0.07
     spons
    0.07
    å¼ıçļĦ
    0.07
    ä¸Ń没æľī
    0.07
    ä¸Ń对
    0.07
    æ¯Ķè¾ĥå¤įæĿĤ
    0.07
    ä¸ŃåIJ«æľī
    0.07
    Activations Density 0.008%

    No Known Activations