© 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. 570
    Prev
    Next
    INDEX
    Explanations

    linking or related items

    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
    hatt
    -0.10
    ewn
    -0.09
    æ¡Ģ
    -0.09
    -La
    -0.09
    èĤĦ
    -0.09
    éľģ
    -0.09
    大çĽĺ
    -0.08
     kurulu
    -0.08
    .processor
    -0.08
    身躯
    -0.08
    POSITIVE LOGITS
    岫
    0.09
    ãī
    0.08
    æĺıè¿·
    0.08
    åģĩåĨĴ
    0.08
    浯
    0.08
    о
    0.07
    AM
    0.07
    å¿ĥä¸ŃçļĦ
    0.07
    /is
    0.07
    ä¸Ķ
    0.07
    Activations Density 0.868%

    No Known Activations