© 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. 6138
    Prev
    Next
    INDEX
    Explanations

    remembering and forgetting

    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
    æ»ĭåij³
    -0.11
    ral
    -0.10
    é¢ĦåijĬ
    -0.09
     rum
    -0.08
    çıº
    -0.08
    å¤ĩ
    -0.08
    .preview
    -0.08
     sab
    -0.08
    urat
    -0.08
    Sab
    -0.08
    POSITIVE LOGITS
    iÄĩ
    0.11
    罡
    0.10
    ä½ıäºĨ
    0.10
    æľªæĪIJå¹´
    0.10
    带走
    0.10
    ä¸įä½ı
    0.10
    ä½łåĸľæ¬¢
    0.09
    æĬ¤èº«
    0.09
    çѵ
    0.09
    亲è¿ij
    0.09
    Activations Density 0.023%

    No Known Activations