© 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. 24254
    Prev
    Next
    INDEX
    Explanations

    rules and regulations

    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
    åºŃ
    -0.10
    æĥł
    -0.09
    åħ»æĪIJ
    -0.09
    çĢļ
    -0.09
    è§Ĵ度
    -0.09
    红è±Ĩ
    -0.08
    å»Ĭ
    -0.08
    ä¸ľæµ·
    -0.08
    èĢķèĢĺ
    -0.08
    oret
    -0.08
    POSITIVE LOGITS
    äºĨä¸ĢäºĽ
    0.11
    erno
    0.11
    äºĨä¸Ģç³»åĪĹ
    0.11
    äºĨä¸Ģ
    0.10
    äºĨä¸Ģ个
    0.10
    äºĨä»ĸçļĦ
    0.10
    äºĨæĪijçļĦ
    0.10
    äºĨä¸Ģ份
    0.10
    äºĨ大éĩıçļĦ
    0.10
    äºĨ
    0.10
    Activations Density 0.348%

    No Known Activations