© 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. 37688
    Prev
    Next
    INDEX
    Explanations

    acid formation

    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
    óc
    -0.07
    izzeria
    -0.07
    iglio
    -0.07
    Ø®ÛĮ
    -0.07
    ouro
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    зон
    -0.07
    SOURCE
    -0.07
    FFE
    -0.07
    'post
    -0.06
    POSITIVE LOGITS
     formation
    0.09
    æĪIJç«ĭ
    0.08
     Formation
    0.08
     létre
    0.08
    æĪIJåŀĭ
    0.08
    çļĦå½¢æĪIJ
    0.08
     formed
    0.08
    formation
    0.07
    æŃ£å¼ıæĪIJç«ĭ
    0.07
    æĪIJç«ĭçļĦ
    0.07
    Activations Density 0.010%

    No Known Activations