© 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. 28338
    Prev
    Next
    INDEX
    Explanations

    action, state, or measure

    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
     offenbar
    -0.08
     aneka
    -0.08
     ordinary
    -0.08
    æĹłé¡»
    -0.08
    è¿Ħä»Ĭ
    -0.08
    encodeURIComponent
    -0.08
    ãĤ¯ãĥ«ãĥŀ
    -0.08
    ordinary
    -0.07
    责任å¿ĥ强
    -0.07
    ucho
    -0.07
    POSITIVE LOGITS
     oftmals
    0.10
     içerisinde
    0.09
     seperate
    0.09
     alot
    0.09
     amongst
    0.09
     anyways
    0.08
    æĽ´åĬłçļĦ
    0.08
     incredibly
    0.08
    -esque
    0.08
    æĪĸæĺ¯
    0.08
    Activations Density 8.175%

    No Known Activations