© 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. 36955
    Prev
    Next
    INDEX
    Explanations

    defensive football positions

    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
    ness
    -0.10
    ç½ij讯
    -0.10
    æĸ°çļĦ
    -0.09
    çĪ¬
    -0.09
    .ylim
    -0.09
    ä¸Ģçľ¼
    -0.09
    ×ķ×Ĺ
    -0.08
    éĺħ
    -0.08
    rus
    -0.08
     hel
    -0.08
    POSITIVE LOGITS
    éĺŁåijĺ
    0.10
    ä½ıäºĨ
    0.09
    åĪ°ä½į
    0.09
    ores
    0.09
    incer
    0.08
    adem
    0.08
    è¿ĻéĩĮéĿ¢
    0.08
    端
    0.08
    ил
    0.08
    æĮ¤
    0.08
    Activations Density 0.005%

    No Known Activations