© 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. 59173
    Prev
    Next
    INDEX
    Explanations

    memorial service remembrance

    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
     errorCallback
    -0.09
    aged
    -0.09
    AGED
    -0.09
    æľ¬ç½ij
    -0.09
    梨
    -0.08
    åĪĨ辨
    -0.08
    洪水
    -0.08
     magn
    -0.08
    æ°´åĬ¡
    -0.08
    ntp
    -0.08
    POSITIVE LOGITS
    广åijĬæľįåĬ¡
    0.10
    èħij
    0.08
     Yad
    0.08
    é¦ĸéĥ½
    0.08
    ä»ĺåĩº
    0.08
    eda
    0.08
     gas
    0.08
    ди
    0.08
    usch
    0.08
    keh
    0.08
    Activations Density 0.003%

    No Known Activations