© 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. 26149
    Prev
    Next
    INDEX
    Explanations

    excuse me

    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
    bez
    -0.09
    utes
    -0.09
    æ¦Ħ
    -0.09
    æī¿
    -0.08
    çģ¿çĥĤ
    -0.08
    çļĦä¿¡ä»»
    -0.08
    èij«èĬ¦
    -0.08
     дов
    -0.08
    ç»Ļå®Ŀå®Ŀ
    -0.08
     EITHER
    -0.08
    POSITIVE LOGITS
    éĹ³
    0.09
    对ä»ĸ们
    0.09
    icy
    0.09
     borrowing
    0.09
    åĵ®
    0.09
     excuse
    0.09
    Exc
    0.09
    ious
    0.09
    æ»´
    0.09
    reso
    0.09
    Activations Density 0.016%

    No Known Activations