© 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. 7299
    Prev
    Next
    INDEX
    Explanations

    cross-pollination, hybridization, and mating

    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
    manifest
    -0.07
     detriment
    -0.07
     manifest
    -0.07
    abwe
    -0.07
    cmp
    -0.06
    oki
    -0.06
    æł¼
    -0.06
    onse
    -0.06
     grate
    -0.06
     heo
    -0.06
    POSITIVE LOGITS
     involving
    0.10
    èĤ²ç§į
    0.08
    æĺ¯ä¸Ģåľº
    0.08
    atson
    0.08
     conducted
    0.08
    åıĮæĸ¹çļĦ
    0.07
    åıĮæĸ¹
    0.07
    趾
    0.07
    AndWait
    0.07
    åıĮæĸ¹åľ¨
    0.07
    Activations Density 0.010%

    No Known Activations