© 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. 59763
    Prev
    Next
    INDEX
    Explanations

    electron shell structure

    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
    æĮ½
    -0.07
    æľ¬åľ°çļĦ
    -0.07
    åĨĴ
    -0.07
    éŨ类
    -0.07
    åħij
    -0.07
     trimming
    -0.07
    å¼ĢæĢĢ
    -0.06
     lagun
    -0.06
    æĭĨ
    -0.06
    infeld
    -0.06
    POSITIVE LOGITS
     electron
    0.10
    çĶµåŃIJ
    0.09
    electron
    0.08
     électron
    0.08
     Electron
    0.08
    鼻åŃIJ
    0.08
     electrons
    0.08
    çļĦçĶµåŃIJ
    0.08
    brero
    0.07
    inna
    0.07
    Activations Density 0.001%

    No Known Activations