© 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. 26134
    Prev
    Next
    INDEX
    Explanations

    job or work

    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
    èĭĦ
    -0.09
    Slides
    -0.09
    íİł
    -0.09
    izia
    -0.09
    fund
    -0.08
    份é¢Ŀ
    -0.08
    colo
    -0.08
    滥
    -0.08
    ê·ľ
    -0.08
    listeners
    -0.08
    POSITIVE LOGITS
    è¿Ļ个èģĮä¸ļ
    0.10
    çļĦç¼ĺæķħ
    0.09
     diss
    0.09
    æŁ³
    0.09
    ä¸ĵä¸ļçļĦ
    0.09
    å·¥ä½ľä¸Ń
    0.09
    1
    0.08
    èģ·
    0.08
    çļĦèģĮä¸ļ
    0.08
    身为
    0.08
    Activations Density 0.094%

    No Known Activations