© 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. 59306
    Prev
    Next
    INDEX
    Explanations

    chromosome

    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
    ìĹ´
    -0.12
    éta
    -0.09
    atura
    -0.09
    æļĿ
    -0.09
    å·
    -0.09
    çİ®
    -0.09
    æIJģ
    -0.09
    æ¦
    -0.09
     inout
    -0.08
    æ¡£
    -0.08
    POSITIVE LOGITS
    zer
    0.10
    åĬłå¿«æİ¨è¿Ľ
    0.09
    éĹªåħī
    0.08
    ursors
    0.08
    æĦį
    0.08
    注æĺİæĿ¥æºIJ
    0.08
     desc
    0.08
    ä¾®
    0.08
    麾
    0.08
    endi
    0.08
    Activations Density 0.082%

    No Known Activations