© 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. 4666
    Prev
    Next
    INDEX
    Explanations

    comma followed by specific noun

    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
    天
    -0.07
    äºĭ
    -0.07
    éħ¥
    -0.06
    aporte
    -0.06
    åħ¨
    -0.06
    åįĥ
    -0.06
    ä¸ĢèĪ¬
    -0.06
    eho
    -0.06
    è¶Ĭ
    -0.06
    éĤ£æĺ¯
    -0.06
    POSITIVE LOGITS
    该èĤ¡
    0.11
    該
    0.11
    该类
    0.11
    该çīĩ
    0.10
    该车
    0.10
    该产åĵģ
    0.10
    该
    0.10
    è¿Ļæī¹
    0.10
    该ä¼ģä¸ļ
    0.09
    å®ĥæľī
    0.09
    Activations Density 0.415%

    No Known Activations