© 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. 54425
    Prev
    Next
    INDEX
    Explanations

    television host or presenter

    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
    èµ°å¾Ĺ
    -0.10
     quot
    -0.09
    ovich
    -0.09
    æī«ä¸Ģæī«
    -0.09
    è°
    -0.08
    è
    -0.08
    errat
    -0.08
    æĪĺåľºä¸Ĭ
    -0.08
    åįģ足
    -0.08
    èĩ³æĸ¼
    -0.08
    POSITIVE LOGITS
    æĽĻ
    0.11
    çıŃåŃIJ
    0.10
    è¾ŀ
    0.09
    æ»Ķ
    0.09
    lund
    0.09
    ullen
    0.09
    è¿Ļ件äºĭ
    0.08
    çĶŁæĢģæĸĩæĺİ
    0.08
     Bust
    0.08
    enchmark
    0.08
    Activations Density 0.028%

    No Known Activations