© 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. 60827
    Prev
    Next
    INDEX
    Explanations

    transitional words

    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
    çĻ¾äº¿
    -0.10
    æ¿ł
    -0.10
    çĪµ
    -0.09
    è¿Ħä»Ĭ为æŃ¢
    -0.09
    à¸ģระà¸Ĺ
    -0.09
    ä¼İ
    -0.09
    约ä¼ļ
    -0.09
    æ²Ĩ
    -0.09
    为ä¹ĭ
    -0.09
    é«ĺå°ļ
    -0.09
    POSITIVE LOGITS
    æĶ¾
    0.10
    Ñıд
    0.09
    æĽ´èĥ½
    0.09
    è¿ĺèĥ½
    0.08
    è¿ĺæľī
    0.08
     grunt
    0.08
    ä¹Łæľī
    0.08
     verw
    0.08
    hr
    0.08
     Lub
    0.08
    Activations Density 0.272%

    No Known Activations