© 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. 59326
    Prev
    Next
    INDEX
    Explanations

    church 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
    ted
    -0.10
    emax
    -0.09
    hots
    -0.09
    身åŃIJ
    -0.09
    inis
    -0.09
    éĢīæĭ
    -0.09
    äºĮåŃĹ
    -0.09
    éĶı
    -0.09
    èĩªè´¸
    -0.09
    terra
    -0.09
    POSITIVE LOGITS
    nee
    0.11
    主è¦ģåİŁåĽł
    0.09
    åłĤ
    0.09
    ä»ĭåħ¥
    0.09
    碧
    0.08
    èļ±
    0.08
    ursors
    0.08
     chor
    0.08
    fab
    0.08
    пл
    0.08
    Activations Density 0.010%

    No Known Activations