© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    reduces complex into simpler or equivalent

    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
    毫
    -0.08
    bud
    -0.07
    åģĩ
    -0.07
    ä¸į太
    -0.07
    éĻIJãĤĬ
    -0.07
     laz
    -0.07
    ÑĤаÑĢи
    -0.07
    REA
    -0.07
     пÑĢедÑĥ
    -0.07
    urio
    -0.06
    POSITIVE LOGITS
     manageable
    0.12
     easier
    0.11
    æĺĵäºİ
    0.09
    æĽ´å®¹æĺĵ
    0.08
     simpler
    0.08
    à¸ĩà¹Īายà¸Ĥึà¹īà¸Ļ
    0.08
    æĽ´æĺĵ
    0.07
    hana
    0.07
    åıĺæĪIJäºĨä¸Ģ个
    0.07
    åıĸèĢĮ代ä¹ĭ
    0.07
    Activations Density 0.024%

    No Known Activations