© 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. 16720
    Prev
    Next
    INDEX
    Explanations

    significant importance

    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
    èĮ«èĮ«
    -0.11
     Rath
    -0.11
    æĤłæĤł
    -0.11
    æŃ£å¥½
    -0.09
    太ä¹ħ
    -0.09
    åħħåĪĨèĤ¯å®ļ
    -0.09
    pedia
    -0.08
    mtx
    -0.08
    æŀģèĩ´
    -0.08
     extrem
    -0.08
    POSITIVE LOGITS
    å®ŀè´¨æĢ§
    0.10
    ALES
    0.09
    éĶı
    0.09
    ixe
    0.08
    æĨ¾
    0.08
    ä¸ĭçıŃ
    0.08
     (>
    0.08
    å¤ļæķ°
    0.08
    ä¸įå°ıçļĦ
    0.08
    å§IJ
    0.08
    Activations Density 0.128%

    No Known Activations