© 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. 7805
    Prev
    Next
    INDEX
    Explanations

    sports leagues and games

    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
    è¿Ħä»Ĭ
    -0.09
    çľģå§Ķ
    -0.09
    æ¼ī
    -0.08
    _surf
    -0.08
    æ³
    -0.08
    åĴ½
    -0.08
    åİ¿å§Ķ
    -0.08
    å©¿
    -0.08
    éĿ¢ç§¯çº¦
    -0.08
     Weinstein
    -0.08
    POSITIVE LOGITS
    壮
    0.10
    clc
    0.09
    å·¡åĽŀ
    0.09
    è§Ĥèµı
    0.09
    壯
    0.09
     televised
    0.09
     stadiums
    0.09
    è·£
    0.09
    ëıĪ
    0.09
    ä½ĵèĤ²å½©ç¥¨
    0.09
    Activations Density 0.127%

    No Known Activations