© 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. 47638
    Prev
    Next
    INDEX
    Explanations

    mitigate, alleviate, propagate, facilitate

    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
    iness
    -0.10
    fully
    -0.10
    liness
    -0.10
    ×ķת
    -0.09
    lessness
    -0.09
    اÙħÙĦ
    -0.09
    itionally
    -0.09
    nap
    -0.09
    /or
    -0.09
    ific
    -0.08
    POSITIVE LOGITS
    eer
    0.13
    ally
    0.12
    ively
    0.12
    ives
    0.12
    ting
    0.11
     giác
    0.10
     groundwork
    0.10
    emas
    0.09
    ÑĤÑĮÑģÑı
    0.09
    кла
    0.09
    Activations Density 0.501%

    No Known Activations