© 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. 14140
    Prev
    Next
    INDEX
    Explanations

    suffix, system, disorder, paradigm

    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
    iw
    -0.07
    ÙĪÙĨÙĩ
    -0.07
    åħ«ä»Ļ
    -0.07
    umis
    -0.07
    æĹ¥æĿ¥
    -0.07
    çľĭæĿ¥
    -0.07
    å·²ç»ıæĺ¯
    -0.07
    åħ¶å®ŀæĺ¯
    -0.07
    ido
    -0.07
    ä½Ĩæĺ¯ä»ĸ
    -0.07
    POSITIVE LOGITS
     whereby
    0.09
    ä¹Łå°±æĺ¯è¯´
    0.08
     wherein
    0.08
    å°±æĺ¯è¯´
    0.08
    åį³åľ¨
    0.08
    __:
    0.08
    _:
    0.08
    æĪĸèĢħ说
    0.08
    [^
    0.07
    [*
    0.07
    Activations Density 0.027%

    No Known Activations