© 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. 47462
    Prev
    Next
    INDEX
    Explanations

    community, academic, and business contexts

    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
    å¤ļå¹´
    -0.10
     chù
    -0.10
    ë°
    -0.09
    对åŃ©åŃIJ
    -0.09
    åįģå¤ļå¹´
    -0.09
    éĢĢä¼ij
    -0.09
    _LEAVE
    -0.09
     chơi
    -0.08
    Playable
    -0.08
    顽
    -0.08
    POSITIVE LOGITS
    æ¯įæł¡
    0.13
    åľ¨æł¡
    0.12
    å¸ĪåħĦ
    0.10
    å®ŀä¹ł
    0.10
    ampus
    0.10
    å¤ĸ交éĥ¨
    0.10
    å¯Ŀ室
    0.09
    模æĭŁ
    0.09
     poster
    0.09
    å¿ĥå¾Ĺ
    0.09
    Activations Density 0.304%

    No Known Activations