© 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. 29426
    Prev
    Next
    INDEX
    Explanations

    amplifier, augments, modules

    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
    çĶµå·¥
    -0.09
     michael
    -0.09
    Ñīа
    -0.09
    æīĪ
    -0.09
    èIJ¦
    -0.08
    basket
    -0.08
    好象
    -0.08
    ä¸īåĪĨ
    -0.08
    æľºåĬ¨
    -0.08
    åĪ¶
    -0.08
    POSITIVE LOGITS
    ipse
    0.09
    åĢĶ
    0.09
    pis
    0.09
     impro
    0.09
    åĪĹ为
    0.09
    èµ·æĿ¥
    0.09
    æį¨ãģ¦
    0.09
    åīįç½®
    0.08
    åīįè¿Ľ
    0.08
    èŁ¾
    0.08
    Activations Density 0.103%

    No Known Activations