© 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. 52114
    Prev
    Next
    INDEX
    Explanations

    oxygen transport and binding

    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
    æĹ¥æĹ¥
    -0.07
    pest
    -0.07
     sandbox
    -0.07
    å¿¿
    -0.07
     probably
    -0.07
     cosm
    -0.07
     Schnitt
    -0.07
    åľ°å¼Ģå±ķ
    -0.07
    åŀĥåľ¾æ¡¶
    -0.07
    èĢĺ
    -0.07
    POSITIVE LOGITS
    è¡Ģ红èĽĭçĻ½
    0.10
     oxygen
    0.10
    æ°§
    0.09
    红ç»Ĩèĥŀ
    0.09
     blood
    0.09
     binding
    0.08
    bind
    0.08
    binding
    0.08
    è¡Ģ液ä¸Ń
    0.08
    endor
    0.08
    Activations Density 0.019%

    No Known Activations