© 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. 63846
    Prev
    Next
    INDEX
    Explanations

    way to

    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
    åı¯èĥ½åĩºçİ°
    -0.09
    ieves
    -0.09
    åĪ°åºķæĺ¯
    -0.08
     ÑģебÑı
    -0.08
    åıĭæĥħ
    -0.08
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    è¡Ķæİ¥
    -0.08
     Ped
    -0.08
    ä¸Ģè§Ĵ
    -0.08
    æѤæĻĤ
    -0.08
    POSITIVE LOGITS
    éĢĶå¾Ħ
    0.11
     пÑĥÑĤ
    0.11
    æĬĬå®ĥ
    0.11
    å°Ĩåħ¶
    0.10
    æĸ¹å¼ı
    0.10
    anner
    0.10
     ë°©ë²ķ
    0.10
    WAY
    0.10
    éĢļè¿ĩ
    0.09
     way
    0.09
    Activations Density 0.118%

    No Known Activations