© 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. 4879
    Prev
    Next
    INDEX
    Explanations

    aging

    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
    ikon
    -0.08
    æİĸ
    -0.08
    æĥĬéŃĤ
    -0.08
    rane
    -0.08
    _SIDE
    -0.08
    çĶŁåij½å®īåħ¨
    -0.08
    Danger
    -0.07
    <table
    -0.07
    åį±æĢ¥
    -0.07
    åį±éļª
    -0.07
    POSITIVE LOGITS
     age
    0.14
    èĢģåĮĸ
    0.14
     aging
    0.14
     ageing
    0.13
     Age
    0.12
    è¡°èĢģ
    0.12
     aged
    0.12
    -aged
    0.11
     Aging
    0.11
    Age
    0.11
    Activations Density 0.120%

    No Known Activations