© 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. 8401
    Prev
    Next
    INDEX
    Explanations

    congenital metabolic

    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
     prevision
    -0.09
    ushman
    -0.09
    Ĥ¤
    -0.08
     cerem
    -0.07
    uder
    -0.07
    ìķĦìĿ´
    -0.07
    dut
    -0.07
    éĩĮè¾¹
    -0.07
    dÃŃ
    -0.07
    å¼Ģå±ķç»ıèIJ¥æ´»åĬ¨
    -0.07
    POSITIVE LOGITS
    å¼ĦèĻļ
    0.07
    èı©
    0.06
    缴æİ¥æĪĸ
    0.06
     ë§Īì°¬
    0.06
    æĪijä¸Ģå®ļ
    0.06
    Lat
    0.06
     beispiels
    0.06
    EST
    0.06
    çĭŃ
    0.06
    æĿ¥è¯´æĺ¯
    0.06
    Activations Density 0.260%

    No Known Activations