© 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. 59302
    Prev
    Next
    INDEX
    Explanations

    answer questions

    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
    -www
    -0.10
    çĽ²
    -0.09
    æĨİ
    -0.09
    nas
    -0.09
    纳
    -0.09
    æĸ·
    -0.09
    渺
    -0.08
    ãĤĦãĤĬ
    -0.08
    uite
    -0.08
    æĸŃ
    -0.08
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.09
    ä¸įæħİ
    0.09
     Dick
    0.09
    éĤ£æł·
    0.08
     Maver
    0.08
    æIJŃ
    0.08
    ISK
    0.08
    解èĦ±
    0.08
    otron
    0.08
    é«ĺè´¨éĩı
    0.08
    Activations Density 0.006%

    No Known Activations