© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    many [category]

    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
    æľīæŶä¼ļ
    -0.10
    æīĢæľīè¿ĻäºĽ
    -0.09
    æľīçĤ¹åĥı
    -0.09
    ä»»ä½ķåħ¶ä»ĸ
    -0.09
    ä¸ĢèĪ¬ä¼ļ
    -0.09
     sometimes
    -0.09
     mainly
    -0.09
    æľīæŶåĢĻ
    -0.09
    æ¯ı次éĥ½
    -0.09
     possibly
    -0.09
    POSITIVE LOGITS
     nowadays
    0.11
    缴æİ¥æĪĸéĹ´æİ¥
    0.10
     تÙĤرÙĬب
    0.09
    —including
    0.09
    çļĦä»Ĭ天
    0.08
    åıªè¦ģä½ł
    0.07
     today
    0.07
     ê·¸ëłĩ
    0.07
    缴æİ¥æĪĸ
    0.07
     including
    0.07
    Activations Density 0.365%

    No Known Activations