© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54914
    Prev
    Next
    INDEX
    Explanations

    sentence endings after commas or conjunctions

    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
    Negative Logits
    ä¹Ŀéĩį
    -0.08
     tÃłn
    -0.07
    ç´¡
    -0.07
    .modify
    -0.07
    łĢ
    -0.07
    æ
    -0.07
    æĮīçħ§åĽ½å®¶
    -0.07
    èı±
    -0.07
    æīĢæľīè¿ĻäºĽ
    -0.07
    olk
    -0.07
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.09
    ä¹Łæľªå¿ħ
    0.07
    åī©ä¸ĭçļĦ
    0.07
    ä¿Ŀåºķ
    0.07
    çļĦä¸Ģå®ļ
    0.07
    åıªåī©ä¸ĭ
    0.07
    ä¹Łä¸įä¸Ģå®ļ
    0.07
    builtin
    0.06
    çŁ³æĻ¯
    0.06
    huis
    0.06
    Activations Density 0.004%

    No Known Activations