© 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. 6153
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
    æ´Ĺæīĭ
    -0.11
    æµij
    -0.09
    åłĥ
    -0.09
    ä»Ģä¹Īåľ°æĸ¹
    -0.09
    åĿĿ
    -0.09
    Counts
    -0.09
    èıľé¸Ł
    -0.09
    íĿ¬
    -0.09
    tur
    -0.09
     Wrapped
    -0.08
    POSITIVE LOGITS
    ÑĢок
    0.10
    ane
    0.09
     Snow
    0.09
    å²ŃåįĹ
    0.09
     snow
    0.09
    snow
    0.08
    гÑĢамм
    0.08
    lean
    0.08
    Snow
    0.08
    æķĻè®Ń
    0.08
    Activations Density 0.074%

    No Known Activations