© 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. 44333
    Prev
    Next
    INDEX
    Explanations

    machinery followed by maize

    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
    ابÙĦ
    -0.07
    ilar
    -0.06
    ä¸įéĢļ
    -0.06
    ấp
    -0.06
    éĺħ
    -0.06
    å°º
    -0.06
    repid
    -0.06
    éĽij貨
    -0.06
    inat
    -0.06
    igli
    -0.06
    POSITIVE LOGITS
    amai
    0.07
    翼翼
    0.07
    anceled
    0.07
    èĮĥæĸĩç½ij
    0.07
    ë°©
    0.07
    è¿Ľ
    0.07
    Ñĥк
    0.07
    ellerie
    0.07
    èµĦæºIJç½ij
    0.06
    enzi
    0.06
    Activations Density 0.055%

    No Known Activations