© 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. 30561
    Prev
    Next
    INDEX
    Explanations

    rate-limiting step or bottleneck

    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
    oyo
    -0.08
    antom
    -0.08
    idd
    -0.07
    elf
    -0.07
    AtA
    -0.07
     Hamp
    -0.07
    диÑģ
    -0.07
    .system
    -0.07
    ays
    -0.07
    æľ¬æĬ¥åijĬ
    -0.07
    POSITIVE LOGITS
     bottleneck
    0.08
     slow
    0.07
    åıijçĶŁåľ¨
    0.07
    éºŁ
    0.07
    çݯèĬĤ
    0.07
    åĴĮ第äºĮ
    0.07
    çļĦæĺ¯ä»Ģä¹Ī
    0.07
    éĢļ常为
    0.06
    çļĦä¸Ģçݯ
    0.06
     main
    0.06
    Activations Density 0.003%

    No Known Activations