© 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. 918
    Prev
    Next
    INDEX
    Explanations

    circulation and recycle processes

    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
    è®´
    -0.10
    糧
    -0.10
    æĪĴ
    -0.09
    饴
    -0.09
    ä¸Ģé¡¿
    -0.09
     Bucc
    -0.09
    大åĬĽæİ¨è¿Ľ
    -0.09
    鸳
    -0.09
    ä¸ĢéĹ´
    -0.09
    éĹ®éĹ®
    -0.09
    POSITIVE LOGITS
    循çݯ
    0.15
    åĽŀæĶ¶
    0.11
    cycle
    0.11
     loop
    0.11
    Loop
    0.11
    _loop
    0.11
     circulation
    0.11
    -loop
    0.10
    loop
    0.10
    	loop
    0.10
    Activations Density 0.121%

    No Known Activations