© 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. 12244
    Prev
    Next
    INDEX
    Explanations

    sports clubs and leagues

    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
    éĢĤåºĶ
    -0.09
    igest
    -0.08
     Ms
    -0.08
    _LA
    -0.08
    åŁİ
    -0.08
    åħĭåĪ¶
    -0.08
    imate
    -0.08
     Digest
    -0.08
    bulk
    -0.08
    综åIJĪå®ŀåĬĽ
    -0.08
    POSITIVE LOGITS
     raft
    0.10
    ä¸ŃèĢĥ
    0.10
    åħ¬çĽĬæĢ§
    0.09
    -caret
    0.09
    INCLUDE
    0.09
    çľģ
    0.09
    è°ļ
    0.09
    çļĦçĪ¶äº²
    0.09
    pillar
    0.09
    家åºŃ
    0.09
    Activations Density 0.207%

    No Known Activations