© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9564
    Prev
    Next
    INDEX
    Explanations

    soap opera drama

    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
    æ£ĺ
    -0.11
    çļĦæľĢåIJİä¸Ģ
    -0.09
    orda
    -0.09
    masters
    -0.08
     MR
    -0.08
    ä¸įä½İäºİ
    -0.08
    çļĦ梦æĥ³
    -0.08
    isson
    -0.08
    çļĦæľºä¼ļ
    -0.08
    CSR
    -0.08
    POSITIVE LOGITS
    inery
    0.11
    isible
    0.09
    RIPT
    0.09
     Uploaded
    0.09
    éĵ¡
    0.09
     má
    0.09
    åį¿
    0.08
    æĪ´
    0.08
    æĶ¾å¿ĥ
    0.08
    ifacts
    0.08
    Activations Density 0.007%

    No Known Activations