© 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. 37492
    Prev
    Next
    INDEX
    Explanations

    conservation of momentum, imation, uning Metal

    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
    vrier
    -0.08
    ubil
    -0.08
    anium
    -0.08
    ERG
    -0.07
    ÙĥÙIJ
    -0.07
    subscriptions
    -0.07
     Martino
    -0.07
    ioctl
    -0.07
    hra
    -0.07
    ä¸Ī
    -0.07
    POSITIVE LOGITS
    ä¸įåıĹ
    0.08
    èį¡
    0.07
    åıĹæįŁ
    0.07
     conservation
    0.07
    äºĭåıĺ
    0.07
    å®ĪæģĴ
    0.06
    æĢ»éĩıçļĦ
    0.06
    ذا
    0.06
     total
    0.06
     violations
    0.06
    Activations Density 0.001%

    No Known Activations