© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56199
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ŀå§ĭ
    -0.09
    ishments
    -0.09
    emean
    -0.09
    èĩªèº«
    -0.08
    榷
    -0.08
    witch
    -0.08
    çľ¼ä¸ĭ
    -0.08
    éĥ¤
    -0.08
    ä¸Ľä¹¦
    -0.08
     fizz
    -0.08
    POSITIVE LOGITS
    Issues
    0.08
    .cal
    0.08
    åŀĵ
    0.08
    ãĥ¼ãĥī
    0.08
    .ipv
    0.07
    åĬłå¿«
    0.07
    .MSG
    0.07
    âĺĴ
    0.07
    å¤ĩèĢĥ
    0.07
    åģ¥åº·äº§ä¸ļ
    0.07
    Activations Density 1.249%

    No Known Activations