© 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. 63942
    Prev
    Next
    INDEX
    Explanations

    one followed by 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
    èįīæ¡Ī
    -0.10
    å®ŀæĥł
    -0.09
    åIJĪéĢĤ
    -0.09
    ä»ĸ们çļĦ
    -0.08
    æł·åŃIJ
    -0.08
    è·Ľ
    -0.08
    èĩ´ä½¿
    -0.08
    ä½Ļ
    -0.08
    åİļåİļ
    -0.08
    å±ĭåŃIJ
    -0.08
    POSITIVE LOGITS
    æIJŃ
    0.10
    ä¸įä»ħè¦ģ
    0.10
    æĦŁè§īåĪ°
    0.09
     oneself
    0.09
    æĦŁåıĹåĪ°äºĨ
    0.09
    æĦŁåıĹåĪ°
    0.09
    æīĢèĥ½
    0.09
    æĦŁåıĹ
    0.09
    çļĦæĥħ绪
    0.09
    åı¯ä»¥æł¹æį®
    0.09
    Activations Density 0.033%

    No Known Activations