© 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. 36878
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and titles

    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
    æĺĶæĹ¥
    -0.09
    å½ĵåľ°æŶéĹ´
    -0.09
     bearing
    -0.08
    ä¹İ
    -0.08
    /respond
    -0.08
    ä¸Ŀ毫ä¸į
    -0.08
    çĨĬ
    -0.08
    Official
    -0.08
    èĩªç§°
    -0.08
    ä¸Ŀ毫
    -0.08
    POSITIVE LOGITS
    çŁ¥éģĵèĩªå·±
    0.09
    æĶ»åĿļ
    0.09
    èµĽåŃ£
    0.09
    æĶ»åĬ¿
    0.09
    人æīįåŁ¹åħ»
    0.09
    身份
    0.09
    æľĢä¼ĺ
    0.09
     пÑĢинÑı
    0.09
    æľĢåĸľæ¬¢çļĦ
    0.08
    çŁ¥éģĵ
    0.08
    Activations Density 0.256%

    No Known Activations