© 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. 29565
    Prev
    Next
    INDEX
    Explanations

    only followed by qualifier

    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
    è¿Ļæł·ä¸Ģ个
    -0.11
    ä»ĸæĺ¯ä¸Ģ个
    -0.10
    (tt
    -0.09
    åī©ä¸ĭçļĦ
    -0.09
    åĪĨä¼ļ
    -0.09
    ä½ķå¤Ħ
    -0.09
    è¿ĻæĶ¯
    -0.09
     minimal
    -0.09
    éĻĨ
    -0.09
    rsa
    -0.09
    POSITIVE LOGITS
    æ¶īåıĬ
    0.09
    æ¶īåıĬåĪ°
    0.09
    mayı
    0.09
    عت
    0.08
     Ere
    0.08
    è·Ŀ
    0.08
    ertext
    0.08
    edReader
    0.08
    åĩºåı£
    0.08
    atif
    0.08
    Activations Density 0.027%

    No Known Activations