© 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. 48881
    Prev
    Next
    INDEX
    Explanations

    addresses, names, and tags

    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
     messing
    -0.06
    ——
    -0.06
    igné
    -0.06
    欣èµı
    -0.06
    ock
    -0.06
     Bethlehem
    -0.06
    (
    -0.06
    iny
    -0.06
    èĵĦ
    -0.06
    POSITIVE LOGITS
    åıijå±ķåĴĮæĶ¹éĿ©
    0.09
    åħĪè¾Ī
    0.09
    æĿ¥æºIJäºİç½ij绾
    0.09
     fadeIn
    0.08
    å¼ĢåıijæľīéĻIJåħ¬åı¸
    0.08
    æŃ¤èµ·
    0.08
    åħ³æ³¨æĪij
    0.08
    æł©æł©
    0.08
    ä¸ŃæĪIJéķ¿
    0.08
    æĸ°èĢģ客æĪ·
    0.08
    Activations Density 0.079%

    No Known Activations