© 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. 44685
    Prev
    Next
    INDEX
    Explanations

    guidelines, training, limits, educate, solve

    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
    Ñģал
    -0.08
    onya
    -0.08
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.08
     selanjutnya
    -0.08
    AndWait
    -0.08
    (Char
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    endl
    -0.07
    æį®æѤæĵįä½ľ
    -0.07
    onial
    -0.07
    POSITIVE LOGITS
     early
    0.07
    éĴĪ对æĢ§çļĦ
    0.07
    æĹ©æľŁ
    0.07
     deep
    0.07
    ire
    0.06
    æĽ´å¤ļåħ³äºİ
    0.06
    èĢģåİ»
    0.06
     Kemen
    0.06
    æĺİç¡®è¦ģæ±Ĥ
    0.06
     robust
    0.06
    Activations Density 0.054%

    No Known Activations