© 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. 7022
    Prev
    Next
    INDEX
    Explanations

    sequence progression

    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
    irit
    -0.07
     Pie
    -0.06
    ä¸įä»ħä»ħ
    -0.06
    acer
    -0.06
    驹
    -0.06
    ces
    -0.06
    abet
    -0.06
    Pie
    -0.06
    åħ»
    -0.06
    为åĩĨ
    -0.06
    POSITIVE LOGITS
    æİ¥èijĹ
    0.09
    à¸ķà¹Īà¸Ńà¹Ħà¸Ľ
    0.09
    继ç»Ń
    0.08
    æİ¥çĿĢ
    0.08
    é¾Ħ
    0.08
    udin
    0.08
    继ç»Ń使çĶ¨
    0.08
    ä¼ļ继ç»Ń
    0.08
    ç¹¼çºĮ
    0.08
    å°Ķæĸ¯
    0.08
    Activations Density 0.017%

    No Known Activations