© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23182
    Prev
    Next
    INDEX
    Explanations

    names and organizations

    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
    ÙĬرÙĩ
    -0.07
    astrophe
    -0.07
    è¾»
    -0.07
    צע
    -0.07
    eliz
    -0.07
    åħħæ²Ľ
    -0.07
    æŃ¤èµ·å½¼
    -0.07
    eck
    -0.06
    åĽ¾ä¹¦ä¸ĵèIJ¥åºĹ
    -0.06
    ugel
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.07
    ë©Ķ
    0.07
    âĢİ
    0.07
    鸳
    0.07
    imed
    0.06
    0.06
     Senior
    0.06
     Council
    0.06
    olith
    0.06
    0.06
    Activations Density 0.748%

    No Known Activations