© 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. 26043
    Prev
    Next
    INDEX
    Explanations

    time remaining

    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
    ILING
    -0.09
    ä¹ħäºĨ
    -0.09
    RIES
    -0.09
    ä¸įæĪIJ
    -0.09
    ä¸įä½ı
    -0.09
    lö
    -0.09
    usher
    -0.08
    æĢ»çĽij
    -0.08
    å°ıå§IJ
    -0.08
    æł¼
    -0.08
    POSITIVE LOGITS
    çīµæĮĤ
    0.10
    ä¼ļå±ķ
    0.09
    ä»ħ为
    0.08
    ä¸Ģ家人
    0.08
    人äºĭ
    0.08
    éĽķ
    0.08
    ho
    0.07
     Webster
    0.07
    ä¸Ģå¹´ä¸Ģ度
    0.07
    çļĦ人çĶŁ
    0.07
    Activations Density 0.013%

    No Known Activations