© 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. 14938
    Prev
    Next
    INDEX
    Explanations

    sequences, population, control, architecture

    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
    _PTR
    -0.08
    å¤ĸäºĭ
    -0.08
     ÙħÙĨا
    -0.07
    dde
    -0.07
    nios
    -0.07
    士æŀĹ
    -0.07
     lumi
    -0.07
    imini
    -0.07
    æĸĹå¿Ĺ
    -0.07
    )->
    -0.07
    POSITIVE LOGITS
    ä¸Ģè§Ī表
    0.08
     versus
    0.08
    åIJĦ级
    0.08
    示æĦı
    0.08
    (left
    0.08
    ä¸įåIJĮæŶ
    0.08
    ä¸Ģè§Ī
    0.08
    åıĬåħ¶
    0.08
     vs
    0.07
     comparison
    0.07
    Activations Density 0.181%

    No Known Activations