© 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. 37445
    Prev
    Next
    INDEX
    Explanations

    dataset and data splits

    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
    è£
    -0.07
    å¼ı
    -0.07
    éĹ´
    -0.07
    èĵī
    -0.07
    æĹłæķ°ä¸ª
    -0.06
    дÑĮ
    -0.06
    å°Ħåĩº
    -0.06
    s
    -0.06
    ç¬
    -0.06
    æĪ®
    -0.06
    POSITIVE LOGITS
    æķ°æį®éĽĨ
    0.11
     dataset
    0.10
    è¿ĻäºĽæķ°æį®
    0.10
     testData
    0.09
     Dataset
    0.09
     datasets
    0.09
    subset
    0.09
    è§ģéĻĦ件
    0.09
    egos
    0.08
    .gz
    0.08
    Activations Density 0.092%

    No Known Activations