© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56811
    Prev
    Next
    INDEX
    Explanations

    code.erase or .matches

    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
    ä¸ĢåĪ»
    -0.07
    rody
    -0.07
    ×Ļ×ĵ
    -0.07
    ESA
    -0.07
    inkan
    -0.06
    浦åĮº
    -0.06
    /swagger
    -0.06
    .Raw
    -0.06
    äºĨçĦ¶
    -0.06
    __((
    -0.06
    POSITIVE LOGITS
    åIJĮçIJĨ
    0.07
     similarly
    0.07
    好åij¢
    0.07
    .reload
    0.07
     seiz
    0.06
    .contentType
    0.06
    åIJĮ人
    0.06
    .site
    0.06
    sher
    0.06
    à·Ļ
    0.06
    Activations Density 0.014%

    No Known Activations