© 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. 19523
    Prev
    Next
    INDEX
    Explanations

    was, were, and be verb forms

    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
    apesh
    -0.07
    /apple
    -0.07
    tog
    -0.07
    usto
    -0.06
    为ä»Ģä¹Īè¦ģ
    -0.06
    dej
    -0.06
    menta
    -0.06
    heed
    -0.06
    наÑģ
    -0.06
    å¹½
    -0.06
    POSITIVE LOGITS
    æĿ¥èĩªäºİ
    0.13
    æºIJäºİ
    0.13
    มาà¸Īาà¸ģ
    0.11
    æĿ¥æºIJäºİ
    0.11
    æºIJèĩª
    0.11
    åĩºèĩª
    0.11
    æĿ¥èĩª
    0.11
    æĺ¯çĶ±
    0.10
    ä¾Ĩèĩª
    0.10
    主è¦ģæĿ¥èĩª
    0.10
    Activations Density 0.366%

    No Known Activations