© 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. 40345
    Prev
    Next
    INDEX
    Explanations

    backyard, yard, garden

    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
     пÑĢиÑĩ
    -0.11
    åı°ä¸Ĭ
    -0.10
    otten
    -0.10
    æ´ĩ
    -0.09
    ikk
    -0.09
    imate
    -0.09
    åĶ¿
    -0.08
    à´¦
    -0.08
    uled
    -0.08
    offs
    -0.08
    POSITIVE LOGITS
    igans
    0.10
    åģļ强
    0.09
    lijke
    0.09
    çļĦéĩįçĤ¹
    0.09
    蹶
    0.09
    æĵĴ
    0.09
     Bliss
    0.09
    iful
    0.09
    æ¹ĥ
    0.08
    ä¸ŃåŃĺåľ¨çļĦ
    0.08
    Activations Density 0.003%

    No Known Activations