© 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. 63986
    Prev
    Next
    INDEX
    Explanations

    frequency of medication or events

    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¿ĩå¾Ĺ
    -0.09
    ç»Ŀ大å¤ļæķ°
    -0.08
    ä¸ĭæ²ī
    -0.08
    åħħ满äºĨ
    -0.08
    æİĺ
    -0.08
    allet
    -0.08
    æ¶Įåħ¥
    -0.08
     Jehovah
    -0.08
    erte
    -0.08
    æĹ¢æľī
    -0.08
    POSITIVE LOGITS
    éĹ´éļĶ
    0.11
    æ¯ı次
    0.10
    第ä¸ī次
    0.10
    ä¸Ģ次
    0.10
    æ¯ıéļĶ
    0.10
    åĩłæ¬¡
    0.09
    çĸıéĢļ
    0.09
     кÑĥÑĢÑģ
    0.09
     íļ
    0.09
    çĸĹç¨ĭ
    0.09
    Activations Density 0.240%

    No Known Activations