© 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. 34034
    Prev
    Next
    INDEX
    Explanations

    occupied, empty, filled, cells, space, site, obstacle

    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
    çļĦä¸Ģå¥Ĺ
    -0.08
    abis
    -0.08
    lieg
    -0.07
    éĿĴ天
    -0.07
    ulat
    -0.07
    .detach
    -0.07
    ä¸Ģå¥Ĺ
    -0.07
    RYPT
    -0.07
    æºIJèĩª
    -0.07
    两å¥Ĺ
    -0.07
    POSITIVE LOGITS
    -filled
    0.09
    filled
    0.08
    å¡«åħħ
    0.08
    空çļĦ
    0.08
     filled
    0.08
     obstacle
    0.08
     obstacles
    0.08
    填满
    0.07
     obstruct
    0.07
     scattered
    0.07
    Activations Density 0.015%

    No Known Activations