© 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. 60099
    Prev
    Next
    INDEX
    Explanations

    sets and set builder notation

    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
    /DTD
    -0.07
    è¿ĻäºĽåĽłç´ł
    -0.07
     complimentary
    -0.07
    .ini
    -0.07
    óis
    -0.07
     combos
    -0.07
    åı£æ°Ķ
    -0.07
    ürk
    -0.06
    ä¼ģä¸ļæĸ°éĹ»
    -0.06
     rot
    -0.06
    POSITIVE LOGITS
     contents
    0.08
    åĪĽä¸ĸ
    0.08
     collections
    0.08
    hood
    0.08
    èĻļ空
    0.07
    _dy
    0.07
    éģį
    0.07
     objects
    0.07
    éĽĨåIJĪ
    0.07
     logically
    0.07
    Activations Density 0.009%

    No Known Activations