© 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. 40153
    Prev
    Next
    INDEX
    Explanations

    by-product

    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
    åħ¨æĹ¥
    -0.11
    ÃŃf
    -0.10
    vice
    -0.10
    atively
    -0.10
    IZED
    -0.09
    åģĥ
    -0.09
    æ¯ıä¸Ģ天
    -0.09
    pery
    -0.09
    ucer
    -0.09
    ocene
    -0.09
    POSITIVE LOGITS
    ields
    0.09
    梦æĥ³
    0.09
    older
    0.09
    rne
    0.09
    entifier
    0.09
    gone
    0.09
    lists
    0.08
    ä»Ħ
    0.08
     luck
    0.08
    product
    0.08
    Activations Density 0.051%

    No Known Activations