© 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. 629
    Prev
    Next
    INDEX
    Explanations

    white supremacist attack

    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
    edly
    -0.11
    广大群ä¼Ĺ
    -0.09
     withString
    -0.09
    åĮĨ
    -0.09
    енд
    -0.09
    æıIJä¾ĽæĽ´å¤ļ
    -0.09
    -vars
    -0.09
    anca
    -0.09
    广大å¸Ĥæ°ij
    -0.09
    èĦijåŃIJ
    -0.09
    POSITIVE LOGITS
    åģ¶å°Ķ
    0.11
     occasional
    0.10
    åĪĿæŃ¥
    0.10
    å·®çĤ¹
    0.09
    çļĦåı¯èĥ½æĢ§
    0.09
     possible
    0.09
     some
    0.09
     некоÑĤоÑĢÑĭе
    0.09
     potential
    0.08
    æľīåı¯èĥ½
    0.08
    Activations Density 1.052%

    No Known Activations