© 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. 51985
    Prev
    Next
    INDEX
    Explanations

    conversational interjections like "hey" and "well"

    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
    achi
    -0.08
     accordingly
    -0.08
    hani
    -0.07
     presid
    -0.07
    èĩªçĦ¶å°±
    -0.07
    دÙĩ
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     ÙĨعÙħ
    -0.06
    æĹłå¥Ī
    -0.06
    POSITIVE LOGITS
    èĪįå¾Ĺ
    0.08
    è¿Ļä¸įæĺ¯
    0.07
    omp
    0.07
    tone
    0.07
    ÙįÙij
    0.06
    halen
    0.06
    æĹłäºĭ
    0.06
    ombo
    0.06
    omat
    0.06
    olet
    0.06
    Activations Density 0.159%

    No Known Activations