© 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. 60815
    Prev
    Next
    INDEX
    Explanations

    video games and strategy

    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
    åħ¥åĽŃ
    -0.10
    å®ļåIJij
    -0.09
    yte
    -0.09
    æģ¼
    -0.09
    çĤ¸
    -0.09
    没æľīæĥ³åĪ°
    -0.09
    AsStream
    -0.08
    åѦç§ij
    -0.08
    .Annotations
    -0.08
    åıĮåIJij
    -0.08
    POSITIVE LOGITS
    æĮº
    0.09
    èģĺçĶ¨
    0.09
    åIJĪ
    0.09
    iring
    0.08
    åħ«åį¦
    0.08
    éĢı
    0.08
    好æĦŁ
    0.08
    ä¿ĺ
    0.08
    .cum
    0.08
     rusty
    0.08
    Activations Density 0.120%

    No Known Activations