© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    profanity and vulgarity

    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
     Germ
    -0.09
    轶
    -0.08
    æĿ¾å¼Ľ
    -0.08
    ä¸ĭå·´
    -0.08
    GLE
    -0.08
    ãģªãģ®
    -0.08
    ä¸ĢäºĮ
    -0.08
    utr
    -0.07
    彩
    -0.07
    ä¸Ģ个å°ı
    -0.07
    POSITIVE LOGITS
    western
    0.10
     wur
    0.09
    iances
    0.08
    loads
    0.08
    浦
    0.08
    zell
    0.08
    çĻ½è¡£
    0.08
    马ä¸Ĭå°±
    0.08
    _wf
    0.08
    iscrim
    0.08
    Activations Density 0.021%

    No Known Activations