© 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. 14956
    Prev
    Next
    INDEX
    Explanations

    bright and brighter

    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¸įåīį
    -0.10
    yled
    -0.09
    èĮĥæĸĩç½ij
    -0.08
    ®
    -0.08
    çük
    -0.08
    åIJįå±±
    -0.08
    ubern
    -0.08
    leman
    -0.08
    alian
    -0.08
    annah
    -0.07
    POSITIVE LOGITS
    ness
    0.10
    ly
    0.09
     اÙĦÙħعاÙĦÙħ
    0.09
    issimi
    0.09
    à¸Ĭัà¸Ķ
    0.09
    zza
    0.09
    issima
    0.08
    -eyed
    0.08
     جدÙĭا
    0.08
     rá»ĩt
    0.08
    Activations Density 0.071%

    No Known Activations