© 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. 26035
    Prev
    Next
    INDEX
    Explanations

    coconut

    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
     kiá»ĩn
    -0.09
    深深çļĦ
    -0.08
    GG
    -0.08
    eon
    -0.08
    erk
    -0.08
    beat
    -0.08
    lev
    -0.08
    fully
    -0.08
    itt
    -0.08
    gg
    -0.08
    POSITIVE LOGITS
    æĬ¥ä¸ļ
    0.10
    achs
    0.10
    å¨ij
    0.10
    æĹ¥æĬ¥ç¤¾
    0.10
    身å¿ĥåģ¥åº·
    0.09
    TouchEvent
    0.09
    åĿŀ
    0.09
    åŀµ
    0.09
    ä¸īäºļ
    0.09
    åł¤
    0.09
    Activations Density 0.013%

    No Known Activations