© 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. 47412
    Prev
    Next
    INDEX
    Explanations

    publish or file except

    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
    Inf
    -0.08
    çĤķ
    -0.08
    æĢİä¹Īä¼ļ
    -0.08
    моÑĢ
    -0.08
    为ä»Ģä¹Īä¸į
    -0.08
     Yam
    -0.08
    ım
    -0.08
    ove
    -0.08
    SO
    -0.08
    GD
    -0.08
    POSITIVE LOGITS
    æľªç»ı
    0.10
    ç½ijç«Ļåľ°åĽ¾
    0.10
     affiliate
    0.09
    æĿ¥çĶµ
    0.09
    æ§Ľ
    0.08
    edReader
    0.08
    ä¸įçĦ¶
    0.08
    楯
    0.08
    .Ma
    0.08
    åIJ¦åĪĻ
    0.08
    Activations Density 0.015%

    No Known Activations