© 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. 44864
    Prev
    Next
    INDEX
    Explanations

    breast milk, pushed images, ejected material, smoke, delivered goods, shipped items, secretions, metastases, lavas, class enrollment

    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
    ##_
    -0.08
    æĥ³è¦ģåľ¨
    -0.08
    ähr
    -0.07
    é«ĺæĢ§èĥ½
    -0.07
    /category
    -0.07
    licenses
    -0.06
     Raymond
    -0.06
    Ø®ÙĬ
    -0.06
    Storyboard
    -0.06
    éĥ½åı¯ä»¥åľ¨
    -0.06
    POSITIVE LOGITS
     nanti
    0.09
    åĩºæĿ¥çļĦ
    0.08
    åıįæĺłåĩº
    0.08
    ä»ĬåIJİçļĦ
    0.08
    sequent
    0.08
    é»ĺ
    0.08
    åĩºä¾ĨçļĦ
    0.08
     withdrawn
    0.07
    )['
    0.07
    orp
    0.07
    Activations Density 0.316%

    No Known Activations