© 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. 40278
    Prev
    Next
    INDEX
    Explanations

    change in quantity or level

    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
    è¿«
    -0.09
    å¤ļä¸ªåĽ½å®¶
    -0.09
    è¿Ļ两年
    -0.09
    åıįæĦŁ
    -0.09
    ä¸Ńå°ıåŀĭ
    -0.09
    å·²ç»ıæľīäºĨ
    -0.09
    涸
    -0.09
    家ä¼Ļ
    -0.09
    grunt
    -0.09
    ä½ľèĢħæīĢæľī
    -0.09
    POSITIVE LOGITS
    bsp
    0.09
    å£ģåŀĴ
    0.09
     emphasis
    0.08
    ìĤ¬ìĿ´
    0.08
    çļĦæĥħ
    0.08
    为æ°ij
    0.08
    åĩºåı£
    0.08
    ielding
    0.08
     synd
    0.08
    xe
    0.08
    Activations Density 0.058%

    No Known Activations