© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26371
    Prev
    Next
    INDEX
    Explanations

    retirement and retiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬åŃIJ
    -0.09
    arest
    -0.09
    约ä¼ļ
    -0.09
     Audi
    -0.09
    ammers
    -0.09
    itia
    -0.09
    å¸ĪåħĦ
    -0.08
    éħ¥
    -0.08
    åĪ»èĭ¦
    -0.08
    åı£æ°´
    -0.08
    POSITIVE LOGITS
    éĢĢä¼ij
    0.29
     retirement
    0.24
     retire
    0.23
    åħ»èĢģéĩij
    0.21
     Retirement
    0.20
     пенÑģи
    0.19
     retired
    0.19
    离éĢĢä¼ij
    0.19
    åħ»èĢģ
    0.18
     retiring
    0.18
    Activations Density 0.107%

    No Known Activations