© 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. 774
    Prev
    Next
    INDEX
    Explanations

    informal/vulgar language

    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
    ä¸Ģç¬Ķ
    -0.11
    åĬĽè¿ĺæĺ¯
    -0.10
    æīĵ好
    -0.10
    ä¸Ģ个éĹ®é¢ĺ
    -0.10
    å¨ģ
    -0.09
    çĶŁäº§è®¾å¤ĩ
    -0.09
    该æĢİä¹Ī
    -0.09
    说çļĦæĺ¯
    -0.09
    vero
    -0.09
    çĦī
    -0.09
    POSITIVE LOGITS
     stuff
    0.22
     Stuff
    0.19
    stuff
    0.17
    _stuff
    0.15
    Stuff
    0.15
    ä¸ľè¥¿
    0.13
     things
    0.11
    çİ©æĦı
    0.11
     shit
    0.11
    çļĦä¸ľè¥¿
    0.10
    Activations Density 0.109%

    No Known Activations