© 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. 4593
    Prev
    Next
    INDEX
    Explanations

    stereoisomers and enantiomers

    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
     hum
    -0.06
    延
    -0.06
    zend
    -0.06
    æľįåĬ¡
    -0.06
     pip
    -0.06
    æ¶Ī磨
    -0.06
    é¦ĸéĥ¨
    -0.06
     Garuda
    -0.06
    çĶ¨å¾Ĺ
    -0.06
    годи
    -0.06
    POSITIVE LOGITS
    äºĴ为
    0.10
    ä¸įå®ĮçļĦ
    0.08
    åIJĮ士
    0.07
    embang
    0.07
    åѤåĦ¿
    0.07
     |–
    0.07
    IRROR
    0.07
     Fleming
    0.07
    .oracle
    0.07
    æĿĥåĪ©ä¹īåĬ¡
    0.07
    Activations Density 0.004%

    No Known Activations