© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11367
    Prev
    Next
    INDEX
    Explanations

    advertising and marketing campaigns

    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
    深交
    -0.11
    ç«ŀ
    -0.09
    å¼Ģåĩº
    -0.09
    å§ĭ建
    -0.09
    ä¾Ľç»Ļ
    -0.09
    è°ĥåīĤ
    -0.09
    ç«ŀäºīåĬĽ
    -0.09
    迹
    -0.09
    çī¹æľĹ
    -0.09
    åIJİæİĴ
    -0.09
    POSITIVE LOGITS
    广åijĬ
    0.17
    代è¨Ģ
    0.16
     rekl
    0.13
     advertisement
    0.13
     commercials
    0.12
     ÑĢеклам
    0.12
     campaigns
    0.12
     campaign
    0.12
    廣åijĬ
    0.12
    代è¨Ģ人
    0.11
    Activations Density 0.120%

    No Known Activations