© 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. 24100
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation and conjunctions

    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
    æ²¾
    -0.12
     вообÑīе
    -0.09
    éļĪ
    -0.08
    å«£
    -0.08
    è¿ĺä¸įéĶĻ
    -0.08
    äºĭæķħåıijçĶŁ
    -0.08
    èĵī
    -0.08
    æĹħ
    -0.08
     minded
    -0.08
    aines
    -0.08
    POSITIVE LOGITS
    使ä¹ĭ
    0.12
    è§Ĩ为
    0.12
    à¹Ħว
    0.10
    涵çĽĸ
    0.10
    使åħ¶
    0.10
    ä»ĸä»¬åľ¨
    0.09
    并åIJij
    0.09
    ä¸įçĪ±
    0.09
    æĺ¯ä¸ºäºĨ
    0.09
    åĪĿè¡·
    0.09
    Activations Density 0.332%

    No Known Activations