© 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. 52230
    Prev
    Next
    INDEX
    Explanations

    cauchy-schwarz inequality

    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
    ä¸ĢåŃĹ
    -0.09
    anat
    -0.09
    nene
    -0.08
     vét
    -0.08
    çĴĭ
    -0.08
    çĤľ
    -0.08
    欢è¿İåIJĦä½į
    -0.08
    istra
    -0.08
    advert
    -0.08
    ISTRA
    -0.08
    POSITIVE LOGITS
     subsequ
    0.07
    ç»Ī
    0.07
     convergence
    0.07
    æĶ¶æķĽ
    0.06
    -se
    0.06
     refinement
    0.06
    æĶ¶
    0.06
     quality
    0.06
    åºĶæĶ¶
    0.06
     progress
    0.06
    Activations Density 0.003%

    No Known Activations