© 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. 24104
    Prev
    Next
    INDEX
    Explanations

    deficiency

    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
    enc
    -0.09
    é¼ĵèĪŀ
    -0.09
    éĩİ
    -0.08
     Carnegie
    -0.08
    æ²®
    -0.08
    åĿıäºĨ
    -0.08
    éĻĦè¿ijçļĦ
    -0.08
    èĩ³ä¸Ĭ
    -0.08
    ä¹°æĪ¿
    -0.08
    çIJ¢ç£¨
    -0.08
    POSITIVE LOGITS
    缺
    0.15
    åĮ®ä¹ı
    0.13
    çŁŃ缺
    0.12
    æIJŃ
    0.11
    严éĩįçļĦ
    0.11
    ä¸į足
    0.10
    缺ä¹ı
    0.10
    èĤĩ
    0.09
    _EPS
    0.09
    mia
    0.09
    Activations Density 0.140%

    No Known Activations