© 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. 26327
    Prev
    Next
    INDEX
    Explanations

    not endorsed or intended

    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
    åİĿ
    -0.10
    oples
    -0.09
    å°Ĭæķ¬
    -0.09
    alg
    -0.08
    æĹ¶æ®µ
    -0.08
    otas
    -0.08
    ultimate
    -0.08
     ultimate
    -0.08
    æ»´
    -0.08
    é«ĺé¢ij
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļèĥ½
    0.12
    代åĬŀ
    0.09
    æ³ķ令
    0.09
     Guar
    0.09
    åĽ´å¢Ļ
    0.09
    æ²®
    0.09
     guar
    0.09
    çĶŁåij½åĬĽ
    0.08
    çĶŁåij½çļĦ
    0.08
    åħ¬å¼Ģåıij
    0.08
    Activations Density 0.012%

    No Known Activations