© 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. 63858
    Prev
    Next
    INDEX
    Explanations

    unique characteristics

    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
    æĪIJåĬŁçİĩ
    -0.11
    æľ«
    -0.08
    人åıĤ
    -0.08
    _RW
    -0.08
     altern
    -0.08
    mor
    -0.08
    acciones
    -0.08
    elt
    -0.08
    clid
    -0.08
    奥迪
    -0.08
    POSITIVE LOGITS
    åı¯çĶ¨
    0.10
    runner
    0.09
    _fixture
    0.09
     restr
    0.09
    çļĦé¢ľèī²
    0.09
    个åŁİå¸Ĥ
    0.09
    宥
    0.08
    æŃ£å¸¸ä½¿çĶ¨
    0.08
     handmade
    0.08
    ç§įåŃIJ
    0.08
    Activations Density 0.107%

    No Known Activations