© 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. 40419
    Prev
    Next
    INDEX
    Explanations

    saturated fats and solutions

    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
    ystore
    -0.09
    liest
    -0.09
    åħ¥ãĤĮ
    -0.09
    ober
    -0.08
    ering
    -0.08
     Proud
    -0.08
    zens
    -0.08
    isle
    -0.08
    é¡»
    -0.08
    .nasa
    -0.08
    POSITIVE LOGITS
    ted
    0.11
    ting
    0.10
    饱åĴĮ
    0.10
     lá»Ļ
    0.09
    飨
    0.09
    æ·¹
    0.09
    ä¸ĩåIJį
    0.09
    çĻ¾å®¶
    0.09
    æīĢæľī人
    0.09
     Alo
    0.09
    Activations Density 0.023%

    No Known Activations