© 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. 63899
    Prev
    Next
    INDEX
    Explanations

    lack of understanding or absence

    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
    ä¸ĢæŶ
    -0.12
    ä¸į容æĺĵ
    -0.11
    ä¸į太
    -0.10
     perfection
    -0.10
    ä¸įä¸Ģå®ļ
    -0.09
    è¿ĺä¸įå¤Ł
    -0.09
    imity
    -0.09
    ä¸įå®ľ
    -0.09
    ä¸įåºĶ
    -0.09
    çľ©
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    ä»»ä½ķ
    0.11
    ä»»ä½ķå½¢å¼ı
    0.11
    çĶļèĩ³æĺ¯
    0.10
    å®ŀéĻħ
    0.10
    羣å®ŀçļĦ
    0.10
    å±ij
    0.10
     ÑħоÑĤÑĮ
    0.10
    æ²¾
    0.10
     вообÑīе
    0.10
    Activations Density 0.143%

    No Known Activations