© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34374
    Prev
    Next
    INDEX
    Explanations

    only or just before

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    å±ħçĦ¶æĺ¯
    -0.08
    ç«Ł
    -0.08
    足足
    -0.08
     dokonce
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
    è°ģ说
    -0.08
    ç«ŁçĦ¶æĺ¯
    -0.07
     persino
    -0.07
    ãģľ
    -0.07
    POSITIVE LOGITS
    èĢĮå·²
    0.14
    ç½¢äºĨ
    0.11
    ä¸įè¿ĩæĺ¯
    0.10
    æĹłéĿŀ
    0.08
    åıªä¸įè¿ĩæĺ¯
    0.08
    éĤ£ä¹Īç®Ģåįķ
    0.07
    åıĪä¸Ģ个
    0.07
    ç½·
    0.07
    ifiable
    0.07
     thôi
    0.07
    Activations Density 0.282%

    No Known Activations