© 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. 44341
    Prev
    Next
    INDEX
    Explanations

    numbers or steps

    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
    ain
    -0.07
    å°¤åħ¶
    -0.07
    ans
    -0.07
    orden
    -0.07
    æĪIJ
    -0.07
    ×ij×Ķ
    -0.06
    å»·
    -0.06
    ãģĮãģĤãĤĭãģ¨
    -0.06
    å¨ģ
    -0.06
    ord
    -0.06
    POSITIVE LOGITS
    earch
    0.09
    ä¼ģä¸ļåıĬ
    0.09
    zÄħ
    0.07
    rgan
    0.07
    æĬĬæı¡ä½ı
    0.07
    èİ·å¾ĹæĽ´å¤ļçļĦ
    0.07
    ä¹ĭä¸ī
    0.07
    elé
    0.07
    зоÑĢ
    0.07
    oria
    0.07
    Activations Density 0.003%

    No Known Activations