© 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. 63918
    Prev
    Next
    INDEX
    Explanations

    future directions and strategies

    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
    isclosed
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.09
    è°ķ
    -0.08
    æĹ¥çħ§
    -0.08
    asics
    -0.08
    çļ±
    -0.08
    æĺ¯åIJ¦ä¼ļ
    -0.08
    erta
    -0.08
    ÑģÑĤан
    -0.08
    duit
    -0.08
    POSITIVE LOGITS
    ä¸ĭä¸ĢæŃ¥
    0.14
    æľªæĿ¥çļĦ
    0.13
     future
    0.13
    æľªæĿ¥
    0.12
    ä¸ĭ次
    0.11
    ä»ĬåIJİ
    0.11
    ä¸ĭä¸Ģ个
    0.11
     next
    0.10
    future
    0.10
    ä¸ĭä¸Ģ
    0.10
    Activations Density 0.116%

    No Known Activations