© 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. 6132
    Prev
    Next
    INDEX
    Explanations

    left and right directions

    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
    丰æĶ¶
    -0.11
    ACT
    -0.10
    actable
    -0.09
    èĿĮ
    -0.09
    å¡
    -0.09
    éĢĥéģ¿
    -0.09
    æĺı
    -0.08
    躲
    -0.08
    å¾ĭ
    -0.08
    æ©IJ
    -0.08
    POSITIVE LOGITS
    å¼Ģåı£
    0.12
    éĺŁ
    0.09
    æ¸IJ
    0.09
    åıĮåIJij
    0.09
    ìŀĶ
    0.09
    æ¬ĬåĪ©
    0.09
    å¼ĢéŨ
    0.08
    rights
    0.08
    åĬŀåħ¬
    0.08
    æķŀ
    0.08
    Activations Density 0.022%

    No Known Activations