© 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. 16644
    Prev
    Next
    INDEX
    Explanations

    factory, manufacturing, equipment

    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
    ä¾®
    -0.09
    çĮ©
    -0.09
    -metadata
    -0.09
    æĮ¯åħ´
    -0.08
     Superior
    -0.08
    för
    -0.08
    ifton
    -0.08
    觥
    -0.08
    æļĸæ°Ķ
    -0.08
    æ¾Ħæ¸ħ
    -0.08
    POSITIVE LOGITS
    åĩºåİĤ
    0.20
    å·¥åİĤ
    0.14
     factory
    0.14
     завод
    0.13
     Factory
    0.12
    factory
    0.12
    åİĤ
    0.11
    (factory
    0.10
    å»ł
    0.10
    laden
    0.10
    Activations Density 0.272%

    No Known Activations