© 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. 64839
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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
    âĢ¦).
    -0.09
    ...).
    -0.09
    âĢ¦âĢ¦ãĢĤ
    -0.09
    ôt
    -0.08
    âĢ¦,
    -0.08
    âĢ¦**
    -0.08
    âĢ¦),
    -0.08
    ag
    -0.08
    âĢ¦)
    -0.08
    âĢ¦*
    -0.08
    POSITIVE LOGITS
    лиÑĤа
    0.09
    nat
    0.09
    ÙĨدÛĮ
    0.09
    inqui
    0.08
    æĸĩç«łæłĩçŃ¾
    0.08
    edReader
    0.08
    #End
    0.08
    নি
    0.08
    stras
    0.08
    ionali
    0.08
    Activations Density 0.036%

    No Known Activations