© 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. 9749
    Prev
    Next
    INDEX
    Explanations

    attachments, blocks, broke

    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
    ered
    -0.08
    åıĪå¦Ĥ
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    ä¸įä¿¡
    -0.07
    ä¹Łåı¯èĥ½æĺ¯
    -0.07
    vv
    -0.06
    ä¹Łåı¯èĥ½
    -0.06
    obiet
    -0.06
    å¦ĤæѤä¸ĢæĿ¥
    -0.06
    ë§Į
    -0.06
    POSITIVE LOGITS
    ooter
    0.07
    à§įদ
    0.07
    oto
    0.07
    æĺ¯ä¸Ģ件
    0.07
    ä¸Ģ天天
    0.06
    æķĻè¾ħ
    0.06
    æ°§éĩı
    0.06
    æĥķ
    0.06
    纶
    0.06
    çļĦæŶåĢĻäºĨ
    0.06
    Activations Density 0.003%

    No Known Activations