© 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. 40255
    Prev
    Next
    INDEX
    Explanations

    array operations or structures

    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
    åħĭæĸ¯
    -0.09
    تÙħ
    -0.09
    缴è¾ĸå¸Ĥ
    -0.09
    åĴĮæĶ¯æĮģ
    -0.09
    ä¸įåıĬ
    -0.09
    reck
    -0.09
    çĻŀ
    -0.09
    ling
    -0.08
    失åĪ©
    -0.08
    管å§Ķä¼ļ
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯
    0.10
    æĪĸå¤ļ
    0.09
     trop
    0.09
    /vector
    0.09
    人éĥ½
    0.08
     Chips
    0.08
    åŀĭ
    0.08
     whose
    0.08
    sWith
    0.08
    åºľ
    0.08
    Activations Density 1.215%

    No Known Activations