© 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. 44780
    Prev
    Next
    INDEX
    Explanations

    patent citations

    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
    ä¸į为
    -0.07
    ä¸Ģæĸ¹
    -0.07
    Ń
    -0.06
     ups
    -0.06
     Ñģебе
    -0.06
    æģ¯
    -0.06
    ÑĢода
    -0.05
     BAS
    -0.05
    âĢ¦
    -0.05
     Umg
    -0.05
    POSITIVE LOGITS
    çľģæ²¹
    0.09
    尼奥
    0.08
     numbered
    0.08
    (ok
    0.08
    rio
    0.08
    LABEL
    0.08
    纳德
    0.08
     paragraphs
    0.08
    代人
    0.08
    ç¼ĸåı·
    0.08
    Activations Density 0.034%

    No Known Activations