© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    gate ion channels

    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
    æ¼ıæ´ŀ
    -0.07
    åħ¥è´¦
    -0.07
    æĮij
    -0.07
    vic
    -0.07
     pid
    -0.07
     vic
    -0.07
     dispens
    -0.06
    ÑĢей
    -0.06
     torn
    -0.06
    renc
    -0.06
    POSITIVE LOGITS
    æĢ¥æĢ¥
    0.07
    å½±
    0.07
    箸
    0.07
    åļĩ
    0.07
    /fontawesome
    0.07
    åIJĵ
    0.07
    .delay
    0.07
    稿
    0.07
    åİŁä»¶åıĬ
    0.07
    æıĥ
    0.07
    Activations Density 0.021%

    No Known Activations