© 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. 52215
    Prev
    Next
    INDEX
    Explanations

    Americans, men, application claims

    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
    åĽ¢ä½ĵ
    -0.09
    å®Įåħ¨æ²¡æľī
    -0.08
    è¿İåIJĪ
    -0.08
     possibly
    -0.08
    综åIJĪä½ĵ
    -0.08
    covering
    -0.07
    履约
    -0.07
     Ä°stanbul
    -0.07
    ving
    -0.07
    åıĤä¸İ
    -0.07
    POSITIVE LOGITS
    æľķ
    0.11
    ä»Ĭ天
    0.10
    åĬ¡
    0.10
    åijĬè¯ī大家
    0.10
    ä»Ĭ天æĪij们
    0.09
     hôm
    0.09
    ç»Ļä½łä»¬
    0.09
    ä»ĬæĻļ
    0.09
    /layouts
    0.09
    åĭĻ
    0.09
    Activations Density 0.090%

    No Known Activations