© 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. 26289
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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
    edList
    -0.10
    kind
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
     kind
    -0.09
    åħ»æĬ¤
    -0.09
    ä¸Ģ级
    -0.09
     KIND
    -0.09
     нек
    -0.08
    .Kind
    -0.08
    åįij
    -0.08
    POSITIVE LOGITS
    éĤ£ä¹Īå¤ļ
    0.13
    çIJĨçĶ±
    0.11
    åĩºè·¯
    0.11
    æľīä»»ä½ķ
    0.10
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.10
    éĤ£ä¹Ī容æĺĵ
    0.10
    ä»»ä½ķ人
    0.10
    zzle
    0.09
    åī©ä¸ĭ
    0.09
    åģľè½¦ä½į
    0.09
    Activations Density 0.080%

    No Known Activations