© 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. 13336
    Prev
    Next
    INDEX
    Explanations

    date and identifier extraction

    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
    å¦ĤæѤä¹ĭ
    -0.07
    /cache
    -0.07
    -modules
    -0.07
    пиÑĤа
    -0.06
    елÑĮ
    -0.06
    tors
    -0.06
    figcaption
    -0.06
     plus
    -0.06
    稿
    -0.06
     supplies
    -0.06
    POSITIVE LOGITS
     пÑĢизна
    0.07
    æĪIJæŃ£
    0.07
    DISPLAY
    0.07
     grouping
    0.07
     varchar
    0.07
    örden
    0.06
    森
    0.06
    VARCHAR
    0.06
    以身
    0.06
     VARCHAR
    0.06
    Activations Density 0.237%

    No Known Activations