© 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. 3676
    Prev
    Next
    INDEX
    Explanations

    employment and work

    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
    å®ĺæĸ¹å¾®ä¿¡
    -0.11
    æĦŁè§¦
    -0.10
    ç¬ı
    -0.09
    åľŁè±ª
    -0.09
    çĥ¦æģ¼
    -0.09
    模æĿ¿
    -0.09
    è¦ģåģļ好
    -0.09
    麻çĥ¦
    -0.09
    າ
    -0.09
    ê¸Ģ
    -0.08
    POSITIVE LOGITS
    å°±ä¸ļ
    0.12
     employment
    0.12
     Employment
    0.10
    çĶ¨å·¥
    0.10
    æĬĢèĥ½åŁ¹è®Ń
    0.09
    濯
    0.09
    å¿¿
    0.09
    帮æī¶
    0.09
    ä¿®å¤į
    0.09
    å®īç½®
    0.09
    Activations Density 0.204%

    No Known Activations