© 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. 40200
    Prev
    Next
    INDEX
    Explanations

    called in

    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
    ãĥŀãĤ¤
    -0.10
    åħ¬å¼Ģåıij
    -0.09
    å¸ĥå°Ķ
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    è¾ĵç»Ļ
    -0.08
     Rising
    -0.08
    èĩªåĪ¶
    -0.08
    addon
    -0.08
    享åıĹ
    -0.08
    å¤ĦåĪĨ
    -0.08
    POSITIVE LOGITS
    çĶ¨æĿ¥
    0.13
    æĺ¯çĶ¨æĿ¥
    0.10
     invoked
    0.10
    ellas
    0.09
    åĩºåĬ¨
    0.09
    æĭ¿æĿ¥
    0.09
    haft
    0.09
    olland
    0.09
    æīij
    0.09
    è´Łè´£
    0.09
    Activations Density 0.160%

    No Known Activations