© 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. 16811
    Prev
    Next
    INDEX
    Explanations

    Nathan or Wesley names

    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
    æ¦Ķ
    -0.11
    ãģĦãĤī
    -0.11
    sons
    -0.09
    æłĬ
    -0.09
    å¤ļä½Ļ
    -0.09
    smith
    -0.09
    éĹ®éĹ®
    -0.09
    sWith
    -0.09
    袱
    -0.08
    ivity
    -0.08
    POSITIVE LOGITS
    ial
    0.10
    bred
    0.09
    aked
    0.09
    éļĶ
    0.08
    æºĥ
    0.08
    illed
    0.08
    åģģ
    0.08
    bron
    0.08
    istory
    0.08
    elf
    0.08
    Activations Density 0.008%

    No Known Activations