© 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. 40123
    Prev
    Next
    INDEX
    Explanations

    millennials and generations

    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
    èĥģ
    -0.10
    ä¸ĵéŨ
    -0.10
    èĪĮ
    -0.09
    寺
    -0.09
    evil
    -0.09
     losers
    -0.09
    _seed
    -0.09
    ä¸ĢåıĮ
    -0.09
    tright
    -0.09
    asio
    -0.09
    POSITIVE LOGITS
    ä¸Ģ代
    0.19
    ä¸ĸ代
    0.17
    æĸ°ä¸Ģ代
    0.16
    年轻人
    0.14
    çļĦ年轻人
    0.14
     Generation
    0.14
    éĿĴå¹´
    0.14
    ä¸ĭä¸Ģ代
    0.14
     generation
    0.14
    Generation
    0.13
    Activations Density 0.086%

    No Known Activations