© 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. 37670
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    haus
    -0.07
    æīĢåIJij
    -0.06
    åľ¨åħ¶ä»ĸ
    -0.06
    è¿ĺæľīåħ¶ä»ĸ
    -0.06
    太
    -0.06
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.06
    aka
    -0.06
    ipes
    -0.06
    åıĬéĥ¨åĪĨ
    -0.06
    Ø£Ùĥ
    -0.06
    POSITIVE LOGITS
     zami
    0.10
    ppo
    0.09
    dere
    0.08
    æŁIJ个
    0.08
     dụ
    0.08
    ä¸ļåĬ¡åıijå±ķ
    0.08
    THREAD
    0.08
     пÑĢедÑģÑĤа
    0.08
     seorang
    0.08
    ä¸Ģä½į
    0.07
    Activations Density 0.037%

    No Known Activations