© 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. 44504
    Prev
    Next
    INDEX
    Explanations

    worth something

    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
    ëĭ¥
    -0.08
    åIJijæĹ¥
    -0.08
    æĬĬ好
    -0.07
    -bind
    -0.07
    iken
    -0.07
    ARAM
    -0.07
    ä¸į好äºĨ
    -0.07
    Invoker
    -0.07
     Notify
    -0.07
    itchens
    -0.07
    POSITIVE LOGITS
    åı«äºº
    0.08
    åĬ¨äºº
    0.08
    iable
    0.07
    人åħ³æ³¨
    0.07
    appable
    0.07
    ä¼Ĺ人
    0.06
    ä¸Ķåħ·æľī
    0.06
    è¿ĻèĪ¬
    0.06
    ห
    0.06
    人å±ħ
    0.06
    Activations Density 0.227%

    No Known Activations