© 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. 55084
    Prev
    Next
    INDEX
    Explanations

    birth years and age groups

    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
    oint
    -0.07
    .Resolve
    -0.07
    å±ħ
    -0.07
    æ±Ĺ
    -0.07
    å¤ľæĻļ
    -0.06
    äºĶæĹ¥
    -0.06
    Ùģظ
    -0.06
    ç§ijåѦåıijå±ķ
    -0.06
     vac
    -0.06
    éĻ¤
    -0.06
    POSITIVE LOGITS
     cohorts
    0.13
    è¿Ļæī¹
    0.11
     cohort
    0.10
    รุà¹Īà¸Ļ
    0.09
    åĩºçĶŁäºİ
    0.09
     поколение
    0.09
    ëħĦìĥĿ
    0.09
    åĩºçĶŁçļĦ
    0.09
    æī¹æ¬¡
    0.09
     รุà¹Īà¸Ļ
    0.09
    Activations Density 0.178%

    No Known Activations