© 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. 57647
    Prev
    Next
    INDEX
    Explanations

    puzzle game, border officer, night vision, osteolysis

    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
    зÑĭв
    -0.08
    rano
    -0.07
    éĽģå¡Ķ
    -0.07
    娲
    -0.07
    èĦļè¸ıå®ŀ
    -0.07
    onga
    -0.07
    æł¡éŨ
    -0.07
    Split
    -0.07
    æģIJæĥ§
    -0.07
    orit
    -0.07
    POSITIVE LOGITS
    /welcome
    0.07
    ä¿ĺ
    0.06
    amp
    0.06
    åħīèį£
    0.06
    oomla
    0.06
    perimental
    0.06
    åģ¥åħ¨
    0.05
    yss
    0.05
    ¯
    0.05
    ä¸Ĭæīĭ
    0.05
    Activations Density 1.011%

    No Known Activations