© 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. 47490
    Prev
    Next
    INDEX
    Explanations

    talking with founder

    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
     ÑģкоÑĢо
    -0.11
    大夫
    -0.09
    ç³Ł
    -0.09
    æݨèįIJéĺħ读
    -0.09
    æ®·
    -0.09
    åĸĥ
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.08
     çıkar
    -0.08
    人çĶŁ
    -0.08
    åŀŃ
    -0.08
    POSITIVE LOGITS
    éĹ®éģĵ
    0.10
    æľī幸
    0.09
    basename
    0.08
    åģļäºĨ
    0.08
    ç¿»è¯ij
    0.08
    æĦĪ
    0.08
    ohn
    0.08
    æ²īæ·Ģ
    0.08
    ä½ľäºĨ
    0.08
    æĢĢæĬ±
    0.08
    Activations Density 0.106%

    No Known Activations