© 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. 40328
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     заÑĢ
    -0.10
    ocol
    -0.09
    管çIJĨåĴĮ
    -0.09
    说çļĦæĺ¯
    -0.09
    è¿ĺä¸įæĺ¯
    -0.09
    éĥ¢
    -0.08
     единÑģÑĤв
    -0.08
    涯
    -0.08
    èĪ¬çļĦ
    -0.08
    ç¢Ľ
    -0.08
    POSITIVE LOGITS
    éĥ½æľīçĿĢ
    0.09
    å¹²èĦĨ
    0.09
    æģĤ
    0.08
    nost
    0.08
     Ach
    0.08
    æľīæĿ¡ä»¶çļĦ
    0.08
    éĥ½æľīèĩªå·±
    0.08
    åĪĨåĮº
    0.08
    åĺīå¹´åįİ
    0.08
    atab
    0.08
    Activations Density 0.031%

    No Known Activations