© 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. 55114
    Prev
    Next
    INDEX
    Explanations

    legal directives and decrees

    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
    ryn
    -0.07
    æŃ£åĢ¼
    -0.07
    igia
    -0.07
     ë²Įìĸ´
    -0.07
    èħ»
    -0.07
    æĥ³å¾ĹåĪ°
    -0.06
    fx
    -0.06
    æıĥ
    -0.06
    综治
    -0.06
    ç¾Ĭ
    -0.06
    POSITIVE LOGITS
    åħ³äºİ
    0.08
     interim
    0.07
    åħĨ
    0.07
    ourcem
    0.07
    Sock
    0.07
    ureka
    0.07
    éĹľæĸ¼
    0.07
     dated
    0.07
    讳
    0.07
    adeon
    0.07
    Activations Density 0.071%

    No Known Activations