© 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. 40131
    Prev
    Next
    INDEX
    Explanations

    inhibition of

    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
    -0.13
    untime
    -0.12
    allen
    -0.10
    inary
    -0.10
    enary
    -0.10
    ä¸İä¼Ĺä¸įåIJĮ
    -0.10
    cing
    -0.09
    èĭĵ
    -0.09
    andise
    -0.09
    åħķ
    -0.09
    POSITIVE LOGITS
    ä½ıäºĨ
    0.12
    ä¸įä½ı
    0.11
    ä¸įäºĨ
    0.09
    ég
    0.09
    å¾Ĺä½ı
    0.08
    itory
    0.08
    äºĨæĪijçļĦ
    0.08
    ä½ı
    0.08
    åīĤ
    0.08
    ä½ľçĶ¨
    0.08
    Activations Density 0.118%

    No Known Activations