© 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. 55706
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun

    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
    åı°çļĦ
    -0.08
    ленÑĮ
    -0.07
    waan
    -0.07
    ä¸Ģç¼ķ
    -0.07
    اÙĪÙĨ
    -0.07
    akis
    -0.07
    åħĭ森
    -0.07
    ä¸Ģ两
    -0.07
    oday
    -0.07
    ×ķ×IJ
    -0.07
    POSITIVE LOGITS
    å´ĩå°ļ
    0.09
     predominantly
    0.09
    å¹ħ
    0.09
     largely
    0.08
    éĢIJ
    0.07
    iesa
    0.07
    -dominated
    0.07
    å¼
    0.07
    çļĦä¸ĸçķĮ
    0.07
    {\"
    0.07
    Activations Density 0.639%

    No Known Activations