© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50762
    Prev
    Next
    INDEX
    Explanations

    start of sentences or list items

    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
     \/
    -0.07
    ./.
    -0.07
    unders
    -0.07
    ingo
    -0.07
    çº¢é¢ľ
    -0.07
    edig
    -0.07
    engkap
    -0.07
    berge
    -0.07
     bâ
    -0.07
     especiales
    -0.07
    POSITIVE LOGITS
      ↵
    0.08
    å¿Į
    0.07
    毫ä¸į
    0.07
    æ³
    0.07
     tiên
    0.07
    é¦ĸåħĪ
    0.06
    åijĬåĪ«
    0.06
    æĺ¯æķ´ä¸ª
    0.06
    ë¶Ģê°Ģ
    0.06
    yto
    0.06
    Activations Density 0.036%

    No Known Activations