© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    database, weather, beer, factory

    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
    βά
    -0.08
    oland
    -0.07
    æĿ¡
    -0.07
    uas
    -0.07
    æ¼ĵ
    -0.07
    ÙĤاÙĦ
    -0.07
    isar
    -0.07
    &S
    -0.07
     PRI
    -0.07
    enes
    -0.07
    POSITIVE LOGITS
    æĦĪ
    0.07
    为ä¾Ŀæį®
    0.06
    terer
    0.06
    ×ĺ×Ļ
    0.06
    éĴĿ
    0.06
    è¶Ĭ
    0.06
    ãĥŀ
    0.06
    妮
    0.06
    èĬĿ
    0.06
    acqu
    0.06
    Activations Density 0.091%

    No Known Activations