© 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. 31531
    Prev
    Next
    INDEX
    Explanations

    trade union

    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
    补水
    -0.09
    ç¥ĵ
    -0.09
    èģĺ请
    -0.09
    anken
    -0.08
    æī¬
    -0.08
    æ½ľ
    -0.08
    ä¿¡æģ¯åıijå¸ĥ
    -0.08
    itm
    -0.08
    å¤ĸéĿ¢
    -0.08
     burg
    -0.08
    POSITIVE LOGITS
    æĢ»å·¥ä¼ļ
    0.14
    å·¥ä¼ļ
    0.14
    工人
    0.13
    åĬ³åĬ¨èĢħ
    0.12
    åħ¨åĽ½
    0.10
    èģĶåIJĪä¼ļ
    0.10
    æĶ¾æĿ¾
    0.10
     Worker
    0.10
     unions
    0.10
    åĬ³åĬ¨
    0.10
    Activations Density 0.132%

    No Known Activations