© 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. 29415
    Prev
    Next
    INDEX
    Explanations

    mainstream practice

    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
     اÙĦÙħÙĩ
    -0.09
    æ²Ľ
    -0.09
    çİ°å®ŀä¸Ń
    -0.09
    åľ¨åĮĹ京
    -0.09
    åĤ
    -0.08
     mission
    -0.08
    å¸
    -0.08
    åĤ¾
    -0.08
    ä¼°
    -0.08
    ç¿ħèĨĢ
    -0.08
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.10
    agers
    0.10
    ä½Ĩåį´
    0.10
    ed
    0.09
    人士
    0.09
    æĻļæĬ¥
    0.09
    ming
    0.09
     Kah
    0.09
    yet
    0.09
    elan
    0.08
    Activations Density 0.008%

    No Known Activations