© 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. 16569
    Prev
    Next
    INDEX
    Explanations

    community center hall club house

    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
    çĭ¬çī¹çļĦ
    -0.11
    ç½ij讯
    -0.10
    elf
    -0.10
    æĺ¯æĢİæł·
    -0.09
    屯
    -0.09
    isches
    -0.09
    æĺ¯ä¸įä¼ļ
    -0.09
    åİĭå®ŀ
    -0.09
    åŀĥåľ¾
    -0.09
    çĿĽ
    -0.09
    POSITIVE LOGITS
     religion
    0.10
    acob
    0.09
     Religion
    0.09
    ç¹ĩ
    0.08
    èĬŃ
    0.08
    åľ¨äº¬
    0.08
    rac
    0.08
     zar
    0.08
    enheim
    0.08
    _REPLY
    0.08
    Activations Density 0.007%

    No Known Activations