© 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. 23744
    Prev
    Next
    INDEX
    Explanations

    example calculations

    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
    éĻ¤äºĨè¦ģ
    -0.08
    åľ¨ä»ĸ们
    -0.07
    å¦Ĥæŀľä¸Ģ个
    -0.07
    åľ¨ä»ĸ
    -0.06
    PLL
    -0.06
    æĹłé¡»
    -0.06
    åįıåķĨ解åĨ³
    -0.06
    人ä¸İ人ä¹ĭéĹ´
    -0.06
    enn
    -0.06
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ä¸į缺
    0.07
    kees
    0.07
    _hal
    0.07
    ingang
    0.07
    uco
    0.07
    ARE
    0.07
    æľŁä¸º
    0.07
    BlockSize
    0.07
    ugn
    0.07
    toc
    0.07
    Activations Density 0.009%

    No Known Activations