© 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. 47469
    Prev
    Next
    INDEX
    Explanations

    events and tickets

    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
    åħĢ
    -0.08
    æļijåģĩ
    -0.08
    èĬ½
    -0.08
     festivals
    -0.08
    æ³¥
    -0.08
    Poster
    -0.08
    æķ´çIJĨ
    -0.08
     Easter
    -0.08
    åģľè½¦
    -0.08
    åĸ·
    -0.08
    POSITIVE LOGITS
    çļĦé£Łçī©
    0.12
    datatable
    0.10
    ixe
    0.10
    港åĮº
    0.10
    èıľåĵģ
    0.09
    èıľåįķ
    0.09
    èıľèĤ´
    0.09
    çļĦä¼ģä¸ļ
    0.09
    åķĨä¼ļ
    0.09
    çŃ·
    0.09
    Activations Density 0.060%

    No Known Activations