© 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. 59905
    Prev
    Next
    INDEX
    Explanations

    definition or declaration

    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
    åĹĵåŃIJ
    -0.07
    बà¤Ĥध
    -0.07
    æł©æł©
    -0.06
     Anschluss
    -0.06
    åįķæĸ¹éĿ¢
    -0.06
     souvenirs
    -0.06
    æĹıèĩªæ²»åİ¿
    -0.06
    êµ°ìļĶ
    -0.06
     Telegraph
    -0.06
    ego
    -0.06
    POSITIVE LOGITS
     thereof
    0.09
     unto
    0.08
    æ·«
    0.08
    åİ»å¤Ħ
    0.08
    ç³»ç»ŁåıĬ
    0.07
    entrata
    0.07
     amongst
    0.07
     contrary
    0.07
    ä¸įèĥ½å¤Ł
    0.07
    éĩĮ头
    0.07
    Activations Density 0.052%

    No Known Activations