© 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. 55128
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.08
    arty
    -0.07
    Å¡te
    -0.07
     almost
    -0.07
    utum
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
     Readonly
    -0.07
    çĽĺæĹĭ
    -0.07
    身边çļĦ人
    -0.07
    Ń
    -0.07
    POSITIVE LOGITS
     ÑĥÑģловии
    0.08
    没æľīåħ¶ä»ĸ
    0.07
    空ä¸Ń
    0.07
    anj
    0.07
     oczywiÅĽcie
    0.06
    ä¸įè¦ģå¿ĺè®°
    0.06
    计
    0.06
    ä¸įå¿ĺ
    0.06
     toutefois
    0.06
    åįĥä¸ĩ
    0.06
    Activations Density 0.033%

    No Known Activations