© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30852
    Prev
    Next
    INDEX
    Explanations

    operate or operates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -bars
    -0.09
    人为
    -0.09
    å¾Ĺèµ·
    -0.09
    ç«ł
    -0.09
    flu
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.08
    AGER
    -0.08
    çĶ¨æĪ·æıIJä¾Ľ
    -0.08
    uxt
    -0.08
    æľ¬ç«Ļ
    -0.08
    POSITIVE LOGITS
     дÑĥÑħ
    0.09
    宵
    0.09
    离ä¸įå¼Ģ
    0.09
    åħį
    0.08
    guided
    0.08
    å®Įåħ¨
    0.08
    ç«¿
    0.08
    å±ŀ
    0.08
    èĤ¡
    0.08
     entirely
    0.08
    Activations Density 0.027%

    No Known Activations