© 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. 52166
    Prev
    Next
    INDEX
    Explanations

    aviators

    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
    天å¤ĸ
    -0.09
    illin
    -0.07
    èĻ½æĺ¯
    -0.07
    建ä¸ļ
    -0.07
    Ñĥбли
    -0.07
    ambang
    -0.07
    å·©åĽº
    -0.07
    çĪ±æĪij
    -0.07
     Lib
    -0.07
    pez
    -0.07
    POSITIVE LOGITS
    好åĥı
    0.09
    å¸ĤåľºçĽijçĿ£ç®¡çIJĨ
    0.07
    appel
    0.07
    好åĥıåľ¨
    0.06
     seeming
    0.06
    éħ¥
    0.06
    称ä¹ĭ为
    0.06
    èĩªçĦ¶èĢĮçĦ¶
    0.06
    ä¸Ģ个åı«
    0.06
    好åĥıæĺ¯
    0.06
    Activations Density 0.220%

    No Known Activations