© 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. 30911
    Prev
    Next
    INDEX
    Explanations

    clothing and decor items

    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
    -0.09
    1
    -0.07
    2
    -0.07
    7
    -0.07
    0
    -0.07
    8
    -0.07
     ...
    -0.07
    åºŀ大
    -0.07
    3
    -0.06
    elon
    -0.06
    POSITIVE LOGITS
     contempora
    0.11
    æĿ¥ä¸ª
    0.11
     subtly
    0.10
     tenden
    0.10
    æĹ¥ä»¥æĿ¥
    0.09
     magari
    0.09
    æĪĸå°ij
    0.09
    нибÑĥдÑĮ
    0.09
    代夫
    0.09
    æĬķèµĦæĪĸ
    0.09
    Activations Density 0.095%

    No Known Activations