© 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. 29780
    Prev
    Next
    INDEX
    Explanations

    science and mathematics fields

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ±æĢ¨
    -0.11
    æIJĤ
    -0.10
    纥
    -0.09
     compliment
    -0.09
    icode
    -0.09
    è¿ijè·Ŀ离
    -0.09
    ä¸ĢéĹ´
    -0.09
    ç¢Ľ
    -0.09
    å·§
    -0.09
    大éħĴåºĹ
    -0.08
    POSITIVE LOGITS
    å¸Ŀçİĭ
    0.10
    åĬĽåº¦
    0.09
    æ¿Ģ
    0.08
    ÑĤок
    0.08
    æ°ijæĶ¿
    0.08
    .Exit
    0.07
    opi
    0.07
     Ñĥни
    0.07
    ãģĭãģij
    0.07
    æĪijåİ»
    0.07
    Activations Density 0.556%

    No Known Activations