© 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. 35537
    Prev
    Next
    INDEX
    Explanations

    numbers, versions, second, decrypt

    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
    æĪijæł¡
    -0.09
    ç½ijåıĭ们
    -0.09
    .addHandler
    -0.09
    æĽ´å¤ļçļĦæĺ¯
    -0.09
    å¾®ç¬ij
    -0.09
    æĪij们åºĶ该
    -0.09
    Spoiler
    -0.09
    моÑĢ
    -0.09
    áĢĦ
    -0.08
    ITIVE
    -0.08
    POSITIVE LOGITS
    对该
    0.12
    æģ°å¥½
    0.10
    éĤ£ä¸ªäºº
    0.08
    _DM
    0.08
    ãģĿãĤĮãĤĴ
    0.08
    çļĦéĤ£ä¸ª
    0.08
    æŁIJæŁIJ
    0.08
    åįĥéĩĮ
    0.08
    ãģĤãģªãģŁ
    0.08
    TMP
    0.08
    Activations Density 0.412%

    No Known Activations