© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    references and documentation

    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
    ÙĤÙģ
    -0.08
    cdc
    -0.07
    jure
    -0.06
    -0.06
    azzi
    -0.06
    _org
    -0.06
    åIJĪçIJĨ
    -0.06
    æĺ¯ä¸Ģ大
    -0.06
    rieve
    -0.06
    ä¸ĬåĬł
    -0.06
    POSITIVE LOGITS
    å¯¹ä½łè¯´
    0.07
    æĸĩç«łæłĩçŃ¾
    0.07
    alda
    0.07
    éĤ£äºĽå¹´
    0.07
     Others
    0.07
    æĪijå¿ĥä¸Ń
    0.07
    åºĦéķĩ
    0.07
    å¹´æľŁ
    0.07
     ['#
    0.07
    æĪijåĴĮæĪijçļĦ
    0.07
    Activations Density 0.003%

    No Known Activations