© 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. 59937
    Prev
    Next
    INDEX
    Explanations

    formal, formulation, pattern

    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
    縱
    -0.09
    imak
    -0.08
    å¾ĭå¸Ī解çŃĶ
    -0.08
    .Script
    -0.08
    å°ı妹
    -0.08
    好æ¯Ķ
    -0.08
    è¿ŀäºij
    -0.08
    æĨ¬
    -0.08
    еÑĢед
    -0.08
    _src
    -0.07
    POSITIVE LOGITS
     formal
    0.09
    æŃ£å¼ı
    0.08
     formally
    0.08
     Formal
    0.07
     ded
    0.07
    æŃ£å¼ıçļĦ
    0.07
     formulation
    0.07
    è¯ģå®ŀ
    0.07
    ä¸Ģä¸Ģ
    0.06
    缸åºĶ
    0.06
    Activations Density 0.142%

    No Known Activations