© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37503
    Prev
    Next
    INDEX
    Explanations

    World Health Organisation or 'WHO'

    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
    棱
    -0.10
    è¾¹
    -0.09
    _bundle
    -0.09
    带ä¸Ĭ
    -0.09
     institutes
    -0.08
    ât
    -0.08
    åĿĬ
    -0.08
    æ±īæĹı
    -0.08
    çĪ±åĽ½ä¸»ä¹ī
    -0.08
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.08
    POSITIVE LOGITS
    èģĶåIJĪåĽ½
    0.19
    åħ¨çIJĥ
    0.18
    åĽ½éĻħå¸Ĥåľº
    0.16
    åĽ½éĻħ
    0.15
    åIJĦåĽ½
    0.15
    æĪIJåijĺåĽ½
    0.14
    åħ¨çIJĥç»ıæµİ
    0.14
     global
    0.14
    åľ¨åħ¨çIJĥ
    0.14
    è·¨åĽ½
    0.14
    Activations Density 0.282%

    No Known Activations