© 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. 63897
    Prev
    Next
    INDEX
    Explanations

    annual

    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
    è¿ijæľŁ
    -0.10
    çıº
    -0.10
    inded
    -0.09
    æĢ¥åī§
    -0.09
    ä»Ĭ天çļĦ
    -0.09
    oup
    -0.09
    强æľīåĬĽçļĦ
    -0.09
    åĮ»çĸĹåį«çĶŁ
    -0.08
     BUF
    -0.08
     Monroe
    -0.08
    POSITIVE LOGITS
    æ¯ıå¹´
    0.18
    ä¸Ģå¹´ä¸Ģ度
    0.17
    æ¯ıå¹´éĥ½
    0.16
     annual
    0.15
    Annual
    0.14
     annually
    0.13
    annual
    0.13
     Annual
    0.13
    年度
    0.13
     yearly
    0.12
    Activations Density 0.125%

    No Known Activations