© 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. 51298
    Prev
    Next
    INDEX
    Explanations

    brute force search

    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
    计éĩı
    -0.08
    éħįå¥Ĺ
    -0.07
    ButtonDown
    -0.07
    nice
    -0.07
    quet
    -0.06
    å¤ĦçIJĨ好
    -0.06
    اÙģظ
    -0.06
    اÙĦب
    -0.06
    æ·®
    -0.06
    ollapse
    -0.06
    POSITIVE LOGITS
     search
    0.20
    æIJľç´¢
    0.19
     Search
    0.18
     searching
    0.18
    search
    0.17
    Search
    0.17
    /search
    0.16
     поиÑģ
    0.16
     searches
    0.16
    -search
    0.16
    Activations Density 0.222%

    No Known Activations