© 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. 59418
    Prev
    Next
    INDEX
    Explanations

    before you can post

    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
    åIJİå¤ĩ
    -0.09
     hereby
    -0.08
     Pey
    -0.08
    ãģ¡ãģ¯
    -0.08
    dek
    -0.08
    è¦ģæĬĬ
    -0.08
     zwar
    -0.08
    Coal
    -0.08
    çļĦæ¯ĶèµĽ
    -0.08
    ibbon
    -0.08
    POSITIVE LOGITS
    æĦıè¯ĨåĪ°
    0.10
     ever
    0.10
    importe
    0.10
    çłĶ究çĶŁ
    0.09
    èĨĽ
    0.09
    æıIJåıĬ
    0.09
    çļĦ羣å®ŀ
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    èģ¿
    0.09
    zelf
    0.09
    Activations Density 0.032%

    No Known Activations