© 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. 8355
    Prev
    Next
    INDEX
    Explanations

    disambiguation pages

    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
    太
    -0.09
    太å¤ļ
    -0.09
    太é«ĺ
    -0.08
    too
    -0.08
    太å¤ļäºĨ
    -0.07
    太大äºĨ
    -0.07
    -too
    -0.07
    太强
    -0.07
    太大
    -0.07
    ly
    -0.07
    POSITIVE LOGITS
     ...
    0.09
     ...,
    0.08
    :...
    0.08
     (...)
    0.07
     ...\
    0.07
    åĨ·äºĨ
    0.07
    ...,
    0.07
    _ACT
    0.07
     ..."
    0.07
    èģĶèĢĥ
    0.07
    Activations Density 0.394%

    No Known Activations