© 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. 7000
    Prev
    Next
    INDEX
    Explanations

    arginine, oxide, pituitary

    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
    ä¸įè¯Ĩ
    -0.07
    ä¾Ľç¨¿
    -0.06
    åİĨ
    -0.06
    inste
    -0.06
    æľīåĪ«
    -0.06
    éĩĮäºļ
    -0.06
     purposes
    -0.06
    è¯Ŀ说
    -0.06
    åIJĮæŶåıĪ
    -0.06
    人æ°ijåħ±åĴĮåĽ½
    -0.06
    POSITIVE LOGITS
    ×¢×ķת
    0.08
    onneur
    0.08
    Õµ
    0.07
    melon
    0.07
    onor
    0.07
    ில
    0.07
    åħį
    0.07
    ilder
    0.07
    Descriptors
    0.06
     dependency
    0.06
    Activations Density 0.081%

    No Known Activations