© 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. 59789
    Prev
    Next
    INDEX
    Explanations

    structural punctuation followed by 'A'

    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
    ì¶ķ
    -0.08
    çĶ¸
    -0.07
    oby
    -0.07
    ajak
    -0.07
    entra
    -0.07
     Wis
    -0.07
    çī¹åĪ«æĺ¯
    -0.07
    essin
    -0.07
    _almost
    -0.07
    eschi
    -0.07
    POSITIVE LOGITS
    phu
    0.07
    éĽĦ
    0.07
    umer
    0.07
     Highlander
    0.07
    é¦
    0.07
    å¼
    0.06
     Pha
    0.06
    ймов
    0.06
    ë°©
    0.06
    ä¸İå°ı
    0.06
    Activations Density 0.034%

    No Known Activations