© 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. 44572
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinal indicators

    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
    åı¦ä¸Ģ
    -0.08
    çļĦåı¦ä¸Ģ
    -0.07
    æij
    -0.06
    åľ¨æŁIJäºĽ
    -0.06
    让æĪijçļĦ
    -0.06
    æ©
    -0.06
    åı¦ä¸Ģæĸ¹
    -0.06
    ÐĿС
    -0.06
    è®
    -0.06
     ÑĤÑĢеÑĤ
    -0.06
    POSITIVE LOGITS
     ìĭľìŀijìľ¼ë¡ľ
    0.09
    Äįin
    0.08
    æľĢæĢķ
    0.07
    ảy
    0.07
    åIJĥçĤ¹
    0.07
    ä¸İåħ¶ä»ĸ
    0.07
    cka
    0.07
    доз
    0.07
    _DISP
    0.07
    åľ¨æľĢ
    0.07
    Activations Density 0.130%

    No Known Activations