© 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. 60752
    Prev
    Next
    INDEX
    Explanations

    with this, with your, with the

    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
    кÑĢÑĥÑĤ
    -0.09
     Ivanka
    -0.08
    央
    -0.08
    .lazy
    -0.08
    .Annotations
    -0.08
    å¼Ģä¼ļ
    -0.08
    çķĽ
    -0.08
    imestone
    -0.08
    è¿ŀè½½
    -0.08
    æĵį
    -0.08
    POSITIVE LOGITS
    è¿Ļ款
    0.11
    äºİæѤ
    0.10
    è¿Ļç¯ĩ
    0.10
    è¿Ļ个ä¸ĸçķĮ
    0.09
    æł¹æºIJ
    0.09
    ç¥ī
    0.09
    ç»®
    0.09
    è¿Ļ个
    0.09
    åı°
    0.08
    象å¾ģ
    0.08
    Activations Density 0.096%

    No Known Activations