© 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. 24081
    Prev
    Next
    INDEX
    Explanations

    recent or future time references

    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
    å¿Ŀ
    -0.11
    еждÑĥ
    -0.09
    æŀµ
    -0.09
    éļıåIJİ
    -0.08
    åı¦ä¸Ģç§į
    -0.08
    æķ´ä¸ªäºº
    -0.08
    getOption
    -0.08
    衾
    -0.08
    .management
    -0.08
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.16
    æ¯Ķå¦Ĥ
    0.14
    尤为
    0.14
    è¿ijæľŁ
    0.13
     recently
    0.13
    è¿Ļä¸Ģ次
    0.13
    çľ¼ä¸ĭ
    0.13
    ä¾ĭå¦Ĥ
    0.12
    å°¤åħ¶
    0.12
    Recently
    0.12
    Activations Density 0.271%

    No Known Activations