© 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. 16777
    Prev
    Next
    INDEX
    Explanations

    accent and voice

    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
    çľ¼çļ®
    -0.09
    çĶŁæ´»ä¹łæĥ¯
    -0.09
    çļĦå¿ĥæĢģ
    -0.09
     localVar
    -0.09
    çĭł
    -0.09
    é£İè²Į
    -0.09
    åIJ¾
    -0.08
     lingu
    -0.08
    atts
    -0.08
    çĶ¨åľ°
    -0.08
    POSITIVE LOGITS
    è¯ļå®ŀ
    0.08
    æľīçļĦ人
    0.08
    Atlas
    0.08
    éĿŀ常æĺİæĺ¾
    0.08
    éĿ´
    0.08
    Cong
    0.08
    çĿ£åĬŀ
    0.08
    ãģ¼
    0.08
    cpy
    0.08
    .Comp
    0.08
    Activations Density 0.004%

    No Known Activations