© 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. 55153
    Prev
    Next
    INDEX
    Explanations

    still I want

    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
    udem
    -0.09
     likewise
    -0.08
    Æ°á»Ŀ
    -0.08
    äºij天
    -0.08
     Likewise
    -0.07
    contents
    -0.07
    áh
    -0.07
     ordinarily
    -0.07
    λÏĮ
    -0.07
    isters
    -0.07
    POSITIVE LOGITS
     STDERR
    0.07
    å¿«åİ»
    0.07
    деÑı
    0.07
    æİĴ
    0.06
    æĪijçŁ¥éģĵäºĨ
    0.06
     $$$
    0.06
     Lal
    0.06
    isional
    0.06
    éķ¿çĿĢ
    0.06
    ush
    0.06
    Activations Density 0.009%

    No Known Activations