© 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. 40698
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
    .Schedule
    -0.09
    eil
    -0.07
    enas
    -0.07
    istus
    -0.07
    ãĤ¯ãĥª
    -0.07
    屿
    -0.07
    itar
    -0.07
    vé
    -0.07
    лое
    -0.07
    leck
    -0.07
    POSITIVE LOGITS
    enska
    0.07
    ½
    0.07
    tpl
    0.07
    ãĥĥãĥī
    0.07
    缸è¾ħ缸æĪIJ
    0.06
    teen
    0.06
    ded
    0.06
    ãĤıãģijãģ§
    0.06
    缸äºĴéħįåIJĪ
    0.06
    åħ¥ãĤĮ
    0.06
    Activations Density 0.172%

    No Known Activations