© 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. 59974
    Prev
    Next
    INDEX
    Explanations

    treatment assessment modules class

    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
    ChangeEvent
    -0.08
    è°ĥæķ´åIJİ
    -0.07
    keley
    -0.07
    entif
    -0.07
    _caps
    -0.06
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.06
    åħ¬ä»Ķ
    -0.06
    istin
    -0.06
    ISTR
    -0.06
    گاÙĨ
    -0.06
    POSITIVE LOGITS
    able
    0.07
    åľ¨èĦ¸ä¸Ĭ
    0.07
    å¿ħç»ı
    0.07
    èĢĮçĶŁ
    0.07
    нÑij
    0.07
    åľ¨èº«
    0.07
     Boeh
    0.07
    nable
    0.07
    åľºä¸ĬçļĦ
    0.07
    åıįè¿ĩæĿ¥
    0.06
    Activations Density 0.051%

    No Known Activations