© 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. 16731
    Prev
    Next
    INDEX
    Explanations

    approaches, exposure, contacted, stimulated, applied, injected

    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
    æīĵå®Į
    -0.07
    ланд
    -0.07
     omin
    -0.06
    çļĦå¿ĥéĩĮ
    -0.06
    ä¸įæĿ¥
    -0.06
    æīįåı¯ä»¥
    -0.06
    ãģĤãģı
    -0.06
    ä¸ĢåºĶ俱åħ¨
    -0.06
    tha
    -0.06
     everybody
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.09
    å°±ä¼ļ产çĶŁ
    0.08
    å°±ä¼ļåĩºçİ°
    0.08
    —even
    0.08
    anaan
    0.08
    ä½łå°±ä¼ļ
    0.08
    åį³ä½¿æĺ¯
    0.08
    ested
    0.08
     getro
    0.07
    缸åħ³æĸĩç«ł
    0.07
    Activations Density 0.183%

    No Known Activations