© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64619
    Prev
    Next
    INDEX
    Explanations

    Most

    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
    è¡·
    -0.10
    以ä¸Ĭå°±æĺ¯
    -0.09
     ebenfalls
    -0.08
    ãģĵãģ¡ãĤīãĤĤ
    -0.08
    enen
    -0.08
     infine
    -0.08
     ÑĤоже
    -0.07
    ä¹Łæĺ¯åįģåĪĨ
    -0.07
    ä»Ĭ度ãģ¯
    -0.07
    åĮª
    -0.07
    POSITIVE LOGITS
     âľĶ
    0.09
    éĢĻä¸Ģé»ŀ
    0.08
    .Second
    0.08
     Secondly
    0.08
    åħ¶æ¬¡
    0.08
     ëijĺ째
    0.07
    äºĮè¦ģ
    0.07
    è¿ĻæĹłçĸij
    0.07
    endregion
    0.07
    åħ¶äºĮ
    0.07
    Activations Density 0.054%

    No Known Activations