© 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. 59210
    Prev
    Next
    INDEX
    Explanations

    newsletter subscription requests

    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
    çī¹éĤĢ
    -0.09
    ترا
    -0.08
    社ä¼ļèµĦæľ¬
    -0.08
    è¿Ļè¯Ŀ
    -0.08
    éĩĬ
    -0.08
    åĮĸ身
    -0.08
    æľ¬ç½ij
    -0.08
    趾
    -0.08
    iliar
    -0.08
    åīĥ
    -0.08
    POSITIVE LOGITS
    订éĺħ
    0.10
    Forge
    0.10
    ä¸įå®ļ
    0.10
    éħįéĢģ
    0.09
     subscribing
    0.09
    mailbox
    0.09
    飬
    0.09
    æŶæķĪ
    0.09
    èį¤
    0.08
    .subscribe
    0.08
    Activations Density 0.049%

    No Known Activations