© 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. 44681
    Prev
    Next
    INDEX
    Explanations

    comparison operators followed by numbers or null

    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
    ä¸įè¿ĩä»ĸ
    -0.07
    è°ģçŁ¥éģĵ
    -0.07
    è©°ãĤģ
    -0.07
    ÙĩÛĮ
    -0.06
    isse
    -0.06
    ÚĨÙĩ
    -0.06
    hy
    -0.06
    бе
    -0.06
    çļĦé«ĺä½İ
    -0.06
    æĢ§å¼º
    -0.06
    POSITIVE LOGITS
    osso
    0.09
    ophobia
    0.09
    /null
    0.08
    /=
    0.08
    -Cs
    0.07
    xffffffff
    0.07
    \L
    0.07
    ÃŃf
    0.07
    &r
    0.07
    à°Ĥà°¡à°¿
    0.07
    Activations Density 0.004%

    No Known Activations