© 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. 64137
    Prev
    Next
    INDEX
    Explanations

    create or open file/data

    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°
    -0.10
    iez
    -0.10
    éĤ£ä»½
    -0.09
    åıĪèĥ½
    -0.09
    çĶ±æѤ
    -0.09
    æĺ¾å¾Ĺ
    -0.09
     обÑıзан
    -0.09
    åĢŁæѤ
    -0.09
    æĭ¼
    -0.09
    åĴ«
    -0.09
    POSITIVE LOGITS
    åħĪæĺ¯
    0.14
    åħĪæĬĬ
    0.11
    ãģ¾ãģļ
    0.11
    åħĪ
    0.11
    çĦ¶åIJİ
    0.10
    äºĭåħĪ
    0.10
    éĢīå®ļ
    0.10
     먼ìłĢ
    0.09
    åħĪè¡Į
    0.09
    åľ¨ä¸Ģ个
    0.09
    Activations Density 0.885%

    No Known Activations