© 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. 12305
    Prev
    Next
    INDEX
    Explanations

    you can expect

    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
    æĪij们认为
    -0.11
    æĪij们çļĦ
    -0.10
    ä»ĸ们çļĦ
    -0.10
    -minded
    -0.10
    éĤ£å°±
    -0.10
    å®ĥçļĦ
    -0.09
    ä½łè¯´
    -0.09
    åŃIJéĩĮ
    -0.09
    è¿Ļä¹Łæĺ¯
    -0.09
    èĢĮåıĪ
    -0.09
    POSITIVE LOGITS
    're
    0.14
    -même
    0.12
    've
    0.12
     bè
    0.12
    -know
    0.11
    nger
    0.11
    zelf
    0.11
    ropa
    0.11
    çļĦ人çĶŁ
    0.10
    ’re
    0.10
    Activations Density 0.299%

    No Known Activations