© 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. 21596
    Prev
    Next
    INDEX
    Explanations

    tv series titles

    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
    æ²īçĶ¸çĶ¸
    -0.07
    åľ¨æľ¬æ¬¡
    -0.07
    æľ¬æ¬¡
    -0.07
    èĨľ
    -0.07
     sector
    -0.07
     pierced
    -0.07
     eBook
    -0.07
    illet
    -0.07
     sectors
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    POSITIVE LOGITS
    æĶ¶è§Ĩçİĩ
    0.11
    æĶ¶è§Ĩ
    0.11
    æĴŃåĩºçļĦ
    0.11
    æ¯ıæľŁ
    0.10
    continu
    0.10
    æĴŃåĩº
    0.10
    tv
    0.10
     airing
    0.10
    æłı缮
    0.09
    å¼ĢæĴŃ
    0.09
    Activations Density 0.784%

    No Known Activations