© 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. 26214
    Prev
    Next
    INDEX
    Explanations

    the superlatives

    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
    hev
    -0.09
     Prev
    -0.08
     Carm
    -0.08
    ä¸Ģ人
    -0.08
    APT
    -0.08
    ä½Ļ
    -0.08
    -language
    -0.08
    èĪŁ
    -0.07
    æĦıåij³
    -0.07
    oner
    -0.07
    POSITIVE LOGITS
    æľĢ好çļĦ
    0.13
    æĥ¯
    0.12
    æľĢéļ¾
    0.11
    æľĢå¿«çļĦ
    0.11
    æľĢ容æĺĵ
    0.10
     most
    0.10
     fier
    0.10
    æľĢãĤĤ
    0.10
    æľĢæľī
    0.10
    æľĢåħ·
    0.10
    Activations Density 0.157%

    No Known Activations