© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14588
    Prev
    Next
    INDEX
    Explanations

    commas followed by common words

    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
    æīĢ以å½ĵ
    -0.09
    æīĢ以è¦ģ
    -0.09
    æīĢ以她
    -0.09
    มิ
    -0.08
    尽管å¦ĤæѤ
    -0.08
    æīĢ以ä»ĸ们
    -0.08
    æīĢ以éľĢè¦ģ
    -0.08
     portanto
    -0.08
    人士表示
    -0.08
    ä¹ŁåĽłæѤ
    -0.08
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.11
    åĪĻ
    0.11
    éĤ£ä¹Ī
    0.11
     maka
    0.10
     thì
    0.10
     ÙģØ¥ÙĨ
    0.10
    éĤ£ä¹Īåľ¨
    0.10
    åĪĻåľ¨
    0.09
    åĪĻ该
    0.09
    åĪĻä¼ļ
    0.08
    Activations Density 0.071%

    No Known Activations