© 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. 20894
    Prev
    Next
    INDEX
    Explanations

    football clubs

    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
    å¥ĭæĸĹ
    -0.10
    .fixture
    -0.09
     пÑĢож
    -0.08
    计éĩı
    -0.08
    åıĤåĬł
    -0.08
     franca
    -0.08
    çłļ
    -0.08
    çīĴ
    -0.08
    æĭ´
    -0.08
    OfFile
    -0.08
    POSITIVE LOGITS
    涡
    0.10
    atisation
    0.09
    çľŁäºº
    0.09
    æĿijéķĩ
    0.09
    ìľĦ
    0.09
    èĤ©
    0.09
    .opts
    0.09
    onomy
    0.09
    èĥ½åģļåĪ°
    0.09
    帽åŃIJ
    0.09
    Activations Density 0.012%

    No Known Activations