© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20086
    Prev
    Next
    INDEX
    Explanations

    expletives and profanity

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éģĩéļ¾
    -0.11
    (Spring
    -0.09
    ião
    -0.09
    æĸ½å±ķ
    -0.09
    çĸı导
    -0.09
    ç©Ĺ
    -0.09
    ç«ĭä½ĵ
    -0.08
    ilight
    -0.08
    åħ³æĢĢ
    -0.08
    å¾Īé«ĺåħ´
    -0.08
    POSITIVE LOGITS
     hell
    0.14
     heck
    0.13
    çİ©æĦı
    0.10
     fuck
    0.10
    å°ıåŃIJ
    0.10
    ä»ĸå¦Ī
    0.10
    hell
    0.10
    踢
    0.09
    ä¸įå°½
    0.09
     Hell
    0.09
    Activations Density 0.035%

    No Known Activations