© 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. 47394
    Prev
    Next
    INDEX
    Explanations

    find you

    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
    稳å®ļ
    -0.09
    æ¿Ģ
    -0.08
    濯
    -0.08
    涵çĽĸ
    -0.08
    SITE
    -0.08
    ä½łçľĭ
    -0.08
    夺
    -0.08
    ptom
    -0.08
    Cover
    -0.08
    woke
    -0.08
    POSITIVE LOGITS
    åľ¨åĵªéĩĮ
    0.12
    æī¾äºĨ
    0.12
    æĥ³æī¾
    0.11
    åģľè½¦ä½į
    0.11
    à¹Ģà¸Īà¸Ń
    0.10
    ä¸ĭä¸Ģ个
    0.10
    踪
    0.10
    认
    0.10
    ðŁĶİ
    0.09
    OrCreate
    0.09
    Activations Density 0.125%

    No Known Activations