© 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. 30806
    Prev
    Next
    INDEX
    Explanations

    nested inner sub query

    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
    _msgs
    -0.09
    ardini
    -0.08
    ابÙĤ
    -0.08
    ãi
    -0.08
    áĥIJáĥĹ
    -0.08
    /GPL
    -0.08
    orry
    -0.08
    akwa
    -0.08
    uckland
    -0.08
    VERTISE
    -0.08
    POSITIVE LOGITS
    åµĮå¥Ĺ
    0.08
    (inner
    0.08
     bracket
    0.08
     nested
    0.08
     parentheses
    0.07
    æľĢæ·±çļĦ
    0.07
    æĭ¬
    0.07
    -inner
    0.06
     inner
    0.06
    most
    0.06
    Activations Density 0.001%

    No Known Activations