© 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. 11775
    Prev
    Next
    INDEX
    Explanations

    working-class socioeconomic deprivation

    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
    master
    -0.10
    ç§ĭåŃ£
    -0.10
    å®īåħ¨ç®¡çIJĨ
    -0.10
    killer
    -0.09
    åºĬä¸Ĭ
    -0.09
    ä¸Ģåı·
    -0.09
    缦
    -0.09
    åĪ³
    -0.09
     cupid
    -0.08
    æݨ广åºĶçĶ¨
    -0.08
    POSITIVE LOGITS
    éĺ¶çº§
    0.10
    工人
    0.09
     Worker
    0.09
    _hierarchy
    0.08
    Jar
    0.08
     worker
    0.08
    èģĮå·¥
    0.08
    æĿł
    0.08
    座
    0.08
    ä¹łæĥ¯
    0.08
    Activations Density 0.285%

    No Known Activations