© 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. 59178
    Prev
    Next
    INDEX
    Explanations

    ground and workers

    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
    æĥĩ
    -0.10
    泡
    -0.09
    ä¾ĽåºĶ
    -0.09
    äºĶå®ĺ
    -0.09
    OOM
    -0.09
    åŁ¹è®ŃæľºæŀĦ
    -0.08
    .soft
    -0.08
    èĸ°
    -0.08
    xdd
    -0.08
    rnd
    -0.08
    POSITIVE LOGITS
    èijº
    0.12
    æªIJ
    0.11
    çĪ¬ä¸Ĭ
    0.11
    禾
    0.10
    å±ĭ顶
    0.09
    æļ´éĽ¨
    0.09
    åĬłçĽĸ
    0.09
    æĶĢ
    0.09
    绵
    0.09
    æİĢèµ·
    0.09
    Activations Density 0.050%

    No Known Activations