© 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. 40431
    Prev
    Next
    INDEX
    Explanations

    names or technical terms

    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
    强迫
    -0.10
    æĬī
    -0.10
    åĶ¾
    -0.09
    erne
    -0.09
    lá
    -0.09
    elf
    -0.08
    çīĩåŃIJ
    -0.08
    ä»Ģä¹Īäºĭæĥħ
    -0.08
    好人
    -0.08
    èµĽåIJİ
    -0.08
    POSITIVE LOGITS
    EGIN
    0.11
    ä¸ļçķĮ
    0.09
    èºģ
    0.09
    å¢ĥ
    0.09
    ä¸Ģ声
    0.09
    íĤ
    0.08
    åĭĥåĭĥ
    0.08
    .eye
    0.08
    对èĩªå·±çļĦ
    0.08
    swagger
    0.08
    Activations Density 0.013%

    No Known Activations