© 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. 29441
    Prev
    Next
    INDEX
    Explanations

    ages of people

    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
    Negative Logits
    ä»ĸæĺ¯ä¸Ģ个
    -0.09
    ÑĢев
    -0.08
    åĬŁå¤«
    -0.08
    åIJ¦åĪĻ
    -0.08
    å®Įåħ¨æĺ¯
    -0.08
    tingham
    -0.08
    çݺ
    -0.08
    âĿİ
    -0.08
     TERM
    -0.08
    æĸ°ä¸ĸ纪
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    eer
    0.09
    à¹ĥà¸Ķ
    0.09
    tÃŃ
    0.09
    EMA
    0.08
    æī°
    0.08
    anan
    0.08
    骶
    0.08
    aland
    0.08
    å¹¿æ³Ľ
    0.08
    Activations Density 0.027%

    No Known Activations