© 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. 27416
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    æīĢ以ä»ĸ
    -0.10
    äºİæĺ¯ä»ĸ
    -0.10
     otherwise
    -0.10
     hence
    -0.10
    ä»İèĢĮ导èĩ´
    -0.10
    ä»İèĢĮ使
    -0.09
     thus
    -0.09
    thus
    -0.09
    äºİæĺ¯
    -0.09
     thereby
    -0.09
    POSITIVE LOGITS
     there
    0.11
    æĪij们åı¯ä»¥
    0.09
     it
    0.08
     ÙĩÙĨاÙĥ
    0.08
     можно
    0.08
    edia
    0.08
     we
    0.07
     ë§IJìĿ´ëĭ¤
    0.07
    話ãģ¯
    0.07
    there
    0.07
    Activations Density 0.401%

    No Known Activations