© 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. 16754
    Prev
    Next
    INDEX
    Explanations

    existence and potential

    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
    ä¸Ģ份
    -0.10
    åĬ¨æijĩ
    -0.10
    稽
    -0.10
    æĸĽ
    -0.09
    åĮħ袱
    -0.09
    èı©
    -0.09
    éĤ£æł·çļĦ
    -0.09
    çĿĢçľ¼äºİ
    -0.09
    åħľ
    -0.09
    飧æĢ§
    -0.09
    POSITIVE LOGITS
    apon
    0.09
    åĴĮå®ĮåĸĦ
    0.08
     Kn
    0.08
    äºĴèģĶ
    0.08
    çµ®
    0.08
    ops
    0.07
    ä¸ĩæĪ·
    0.07
    uria
    0.07
    ->__
    0.07
    unga
    0.07
    Activations Density 0.187%

    No Known Activations