© 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. 44336
    Prev
    Next
    INDEX
    Explanations

    atherosclerosis conditions beta disease

    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
    egos
    -0.08
    stech
    -0.08
    .appendTo
    -0.08
    leftright
    -0.07
    SWG
    -0.07
    å®ķ
    -0.07
    ETTO
    -0.07
    ProgressDialog
    -0.07
    ulam
    -0.07
    ariah
    -0.07
    POSITIVE LOGITS
    åıªè¦ģæĺ¯
    0.07
    typ
    0.07
    åĽłä¸ºæĺ¯
    0.07
    èĢĮä¸įæĺ¯
    0.07
    åıªè¦ģèĥ½
    0.06
     Sem
    0.06
    áĥIJáĥĵ
    0.06
    æł¹æľ¬ä¸Ĭ
    0.06
    åѤç«ĭ
    0.06
    ÐļС
    0.06
    Activations Density 0.306%

    No Known Activations