© 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. 52204
    Prev
    Next
    INDEX
    Explanations

    electroluminescence organic

    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
    ÙĪÙĨا
    -0.07
    çĻ½é¹Ń
    -0.07
    åľ¨åģļ好
    -0.07
    Ñĥж
    -0.07
    纵è§Ĥ
    -0.07
     manches
    -0.07
     Payne
    -0.07
    odd
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    atea
    -0.07
    POSITIVE LOGITS
    ëĿ¼ëıĦ
    0.08
    æľīæĪIJ
    0.08
    pite
    0.07
    ?url
    0.07
    Prime
    0.06
    elin
    0.06
    chn
    0.06
    пп
    0.06
    ä¾ĿåŃĺ
    0.06
    尽责
    0.06
    Activations Density 0.002%

    No Known Activations