© 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. 6282
    Prev
    Next
    INDEX
    Explanations

    insulin release

    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
    è¾Ī
    -0.10
    æİĸ
    -0.09
    å¯ĨåĪĩ
    -0.09
    çĭł
    -0.09
    å¯ĨåĪĩåħ³æ³¨
    -0.08
    /cop
    -0.08
    èħIJè´¥
    -0.08
    çıª
    -0.08
    upa
    -0.08
     Watch
    -0.08
    POSITIVE LOGITS
    åĵį
    0.10
    çļĦå£°éŁ³
    0.09
    å®ŀ
    0.09
    anic
    0.09
    razier
    0.08
    fant
    0.08
    èĩ³ä¸Ĭ
    0.08
    使人
    0.08
     лÑĥÑĩ
    0.08
    让人
    0.08
    Activations Density 0.104%

    No Known Activations