© 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. 30368
    Prev
    Next
    INDEX
    Explanations

    peace or perish

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłå½¢
    -0.10
    èĽĽ
    -0.09
    ä¸Ģçľ¼
    -0.09
    å®īåħ¨éļIJæĤ£
    -0.08
    å¿ĺè®°äºĨ
    -0.08
    çªĦ
    -0.08
    å¼¹æĢ§
    -0.08
    è¦ģåѦä¼ļ
    -0.08
    åį·
    -0.08
    éĿĵ丽
    -0.08
    POSITIVE LOGITS
    åĵī
    0.10
     век
    0.10
    åıĪä¸Ģ次
    0.09
     amen
    0.09
    æĦ¿
    0.09
    .backward
    0.09
    пиÑģÑĮ
    0.09
     Skate
    0.09
    åģļ个
    0.08
    å½¼æѤ
    0.08
    Activations Density 0.049%

    No Known Activations