© 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. 59110
    Prev
    Next
    INDEX
    Explanations

    yourself online

    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¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.07
    bag
    -0.07
    igit
    -0.07
    ä¸įåĪ°
    -0.07
    ä¹Łä¸įè¿ĩ
    -0.07
    å¯Ŀ
    -0.06
     Walton
    -0.06
    mos
    -0.06
    -ish
    -0.06
    åįİ丽çļĦ
    -0.06
    POSITIVE LOGITS
    æl
    0.08
    çĶļèĩ³æĺ¯
    0.08
    rÃł
    0.07
    çĶļèĩ³æľī
    0.07
    rov
    0.07
    åıijåijĨ
    0.07
    çĶļèĩ³è¿ĺæľī
    0.07
    è¿ĺåı¯ä»¥åľ¨
    0.07
    æľ¬èº«å°±æĺ¯
    0.07
    åħ¶ä»ĸåľ°åĮº
    0.07
    Activations Density 0.003%

    No Known Activations