© 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. 706
    Prev
    Next
    INDEX
    Explanations

    Jesus and disciples

    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
    ugh
    -0.09
    ingen
    -0.08
    kola
    -0.08
    olib
    -0.07
    åįıåĴĮ
    -0.07
    ingers
    -0.07
    èĴĻå¾·
    -0.07
    èĴ¸çħ®
    -0.07
     Ñİби
    -0.07
    ython
    -0.07
    POSITIVE LOGITS
     Jesus
    0.09
     disciples
    0.08
    Jesus
    0.08
    èĢ¶ç¨£
    0.08
     Yesus
    0.08
    åĪºå®¢
    0.08
    è´¢ç¨İ
    0.07
     discÃŃp
    0.07
    éĴī
    0.07
     disciple
    0.07
    Activations Density 0.045%

    No Known Activations