© 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. 40182
    Prev
    Next
    INDEX
    Explanations

    astaxanthin, condiment, akismet

    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
    utilus
    -0.09
    ELY
    -0.09
    olid
    -0.09
    åĮĸ身
    -0.09
    ãģĺ
    -0.08
    é«ĺå°Ķ
    -0.08
    ึà¸ģ
    -0.08
    æij
    -0.08
    踽
    -0.08
    ibil
    -0.08
    POSITIVE LOGITS
    bung
    0.09
    maker
    0.09
    isse
    0.09
    æŃ¡
    0.09
     igen
    0.09
    makers
    0.08
    ç´«
    0.08
    agen
    0.08
    arris
    0.08
    æ´¼
    0.08
    Activations Density 0.002%

    No Known Activations