© 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. 8940
    Prev
    Next
    INDEX
    Explanations

    encyclopedias and reference books

    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¸ĭåIJĮ
    -0.08
    ekan
    -0.07
    Occurred
    -0.07
    èĵĦ
    -0.07
    endis
    -0.07
    ierge
    -0.06
    ønd
    -0.06
    ancis
    -0.06
    ==="
    -0.06
    以ä¸ĭåĩłçĤ¹
    -0.06
    POSITIVE LOGITS
     handbook
    0.10
     Handbook
    0.08
    ä¸Ľä¹¦
    0.08
     Paperback
    0.07
    é¢Ĩ导干éĥ¨
    0.07
    æīĭåĨĮ
    0.07
     vols
    0.07
    [M
    0.07
    æĦıè¯Ĩ
    0.07
     workbook
    0.06
    Activations Density 0.056%

    No Known Activations