© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50747
    Prev
    Next
    INDEX
    Explanations

    ordered lists or sequences

    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
    Not in Any Lists

    No Comments

    Negative Logits
    stinence
    -0.07
    çļĦåīį
    -0.06
    æĿ¥å¾Ģ
    -0.06
    è¿Ļä¹Ī好
    -0.06
    ä¾ĿèĪĬ
    -0.06
    æ½
    -0.06
    borough
    -0.06
    ìĸ´ëıĦ
    -0.06
    _accum
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİå°±
    0.13
     rá»ĵi
    0.13
     puis
    0.13
    çĦ¶åIJİåĨį
    0.12
    çĦ¶å¾Į
    0.11
    çĦ¶åIJİ
    0.11
     Ø«Ùħ
    0.10
    æľĢç»Ī以
    0.09
    à¹ģลà¹īวà¸ģà¹ĩ
    0.09
    çĦ¶åIJİåıĪ
    0.09
    Activations Density 0.198%

    No Known Activations