© 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. 25087
    Prev
    Next
    INDEX
    Explanations

    CO2 and PO2 pressure

    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
    ắp
    -0.08
    loe
    -0.08
    ä¸įè¾ŀ
    -0.08
    ëĶ
    -0.08
    zeitig
    -0.08
    arité
    -0.07
    othe
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    linear
    -0.07
    çĶŁçĹħäºĨ
    -0.07
    POSITIVE LOGITS
    èĪĴ
    0.07
     exert
    0.07
     Gunn
    0.07
    æݧåĪ¶å¥½
    0.06
    åİ¥
    0.06
    æĹłä¸º
    0.06
    æ°´å¹³
    0.06
    æİĴ
    0.06
    æģŃ
    0.06
    æİĴåĩº
    0.06
    Activations Density 0.008%

    No Known Activations