© 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. 26271
    Prev
    Next
    INDEX
    Explanations

    capital city, punishment, market, name

    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
    est
    -0.11
    çħ
    -0.11
    ingly
    -0.09
    åīįæīĢ
    -0.09
    ulia
    -0.09
    alyzer
    -0.09
    edin
    -0.09
    elves
    -0.09
    лем
    -0.09
     dÃłng
    -0.09
    POSITIVE LOGITS
    ization
    0.15
    ized
    0.14
    izes
    0.13
    ised
    0.13
    istic
    0.13
    izing
    0.11
    izers
    0.11
    ize
    0.11
    isation
    0.11
    icious
    0.11
    Activations Density 0.017%

    No Known Activations