© 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. 48291
    Prev
    Next
    INDEX
    Explanations

    try something

    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
    onnier
    -0.10
    à¥įरà¥Ģ
    -0.09
    ersp
    -0.09
    à¥ĩशन
    -0.09
    aglio
    -0.09
    ibur
    -0.09
    ór
    -0.09
    ër
    -0.09
    ERGE
    -0.08
     гоÑĤовноÑģÑĤи
    -0.08
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.08
    以ä¸ĭæĸ¹å¼ı
    0.07
    åĪ°çļĦ
    0.07
     alternative
    0.07
    :
    0.07
     different
    0.07
    ...
    0.07
    å°Ŀè¯ķ
    0.07
    able
    0.07
    entially
    0.07
    Activations Density 0.077%

    No Known Activations