© 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. 52327
    Prev
    Next
    INDEX
    Explanations

    competition and competitors

    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
    æĥ³ä¸įåĪ°
    -0.11
    rieb
    -0.09
    ä¸įåIJĮäºİ
    -0.09
    çĺł
    -0.08
    ürn
    -0.08
    alien
    -0.08
    èµŀèµı
    -0.08
    æį¢æĪIJ
    -0.08
    éĹ®éĹ®
    -0.08
     nông
    -0.08
    POSITIVE LOGITS
     competing
    0.15
    ç«ŀäºī对æīĭ
    0.13
    ç«ŀäºī
    0.11
     competitors
    0.10
     competitor
    0.10
    åIJĮè¡Į
    0.10
    å¸Ĥåľºç«ŀäºī
    0.10
    åIJĮç±»
    0.10
    igar
    0.09
    å·²ç»ıæľīäºĨ
    0.09
    Activations Density 0.082%

    No Known Activations