© 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. 44437
    Prev
    Next
    INDEX
    Explanations

    approaches and methods

    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
    atcher
    -0.07
    æĩµæĩĤ
    -0.07
    æł¸å¿ĥä»·åĢ¼
    -0.07
    åŁºæľ¬æ¦Ĥ念
    -0.07
    æĺ¯ä¸įåı¯
    -0.06
    ski
    -0.06
    ordo
    -0.06
    격ìĿĦ
    -0.06
    åħ·æľīéĩįè¦ģ
    -0.06
    å°ĨæĮīçħ§
    -0.06
    POSITIVE LOGITS
    æīĭ段
    0.17
     ways
    0.16
    æݪæĸ½
    0.16
    çļĦæīĭ段
    0.15
    åĬŀæ³ķ
    0.15
     methods
    0.15
    çļĦåĬŀæ³ķ
    0.14
    æľīæķĪæݪæĸ½
    0.13
    æĸ¹æ³ķæĿ¥
    0.13
    çŃīæīĭ段
    0.13
    Activations Density 0.601%

    No Known Activations