© 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. 9633
    Prev
    Next
    INDEX
    Explanations

    advocate and advocacy

    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
    éģµå®Ī
    -0.10
    dÃŃ
    -0.10
    OFF
    -0.09
    éľĪ
    -0.09
    举è¡ĮäºĨ
    -0.09
    建设åĴĮ
    -0.09
    é¢Ħå®ļ
    -0.09
    haus
    -0.09
    æ¼Ĥ
    -0.09
    寥
    -0.09
    POSITIVE LOGITS
     advocacy
    0.11
    代è¨Ģ
    0.10
    æݨ广åºĶçĶ¨
    0.10
     Advoc
    0.10
     обÑĢаÑĤ
    0.09
     advocating
    0.09
     advocate
    0.09
    çݰ身
    0.09
    åıį
    0.09
    ä¼łéĢĴ
    0.09
    Activations Density 0.096%

    No Known Activations