© 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. 37710
    Prev
    Next
    INDEX
    Explanations

    genome size

    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
    lish
    -0.08
    indy
    -0.07
    驹
    -0.07
    åı¤å±ĭ
    -0.07
     bulundu
    -0.07
    æĹ¶ä½¿çĶ¨
    -0.07
    è¯Ģ
    -0.07
     actualidad
    -0.06
    çļĦçī¹çĤ¹
    -0.06
    _animation
    -0.06
    POSITIVE LOGITS
    incar
    0.07
    æķ´å¥Ĺ
    0.07
     underlying
    0.07
    åŁºç¡ĢæĢ§
    0.07
     fortunes
    0.07
    IfExists
    0.07
    æŁIJäºĽ
    0.07
    æĮĩçĿĢ
    0.07
    ä¹Łéļıä¹ĭ
    0.07
    atos
    0.07
    Activations Density 0.418%

    No Known Activations