© 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. 29446
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    quo
    -0.08
    æIJĤ
    -0.08
    ROW
    -0.08
    å¿Ŀ
    -0.08
    éĢı
    -0.08
    åĮĨ
    -0.08
    âĺ¼
    -0.08
    æĥº
    -0.08
    âľį
    -0.08
    äºļ马
    -0.08
    POSITIVE LOGITS
     —
    0.10
    éĹ¯
    0.10
    åħ±å»º
    0.09
     главное
    0.09
    æľĢç»Ī
    0.09
    çĶļèĩ³æĺ¯
    0.09
    ç¼Ķ
    0.08
    heimer
    0.08
     ABOVE
    0.08
    èĢĮæĪIJ
    0.08
    Activations Density 0.177%

    No Known Activations