© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    time to time

    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
    æįŀ
    -0.09
    å©ļåIJİ
    -0.09
    ä¸įä¸Ĭ
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.08
    ollah
    -0.08
    åĬ²
    -0.08
    éĻ¤æѤä¹ĭå¤ĸ
    -0.08
    åĪĿ次
    -0.08
    acho
    -0.08
    elli
    -0.08
    POSITIVE LOGITS
     xuyên
    0.10
    åħ®
    0.10
    èĻ¬
    0.09
    客
    0.09
    ä¸Ĭæ¼Ķ
    0.09
    éĩİçĶŁ
    0.09
    è¾Ĺ转
    0.08
    .setDefault
    0.08
    以åIJİ
    0.08
    çĭĢæ³ģ
    0.08
    Activations Density 0.006%

    No Known Activations