© 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. 52285
    Prev
    Next
    INDEX
    Explanations

    FIFA World Cup

    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
    ate
    -0.09
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
    鹫
    -0.09
    ifers
    -0.09
    Benchmark
    -0.08
    benchmark
    -0.08
    unday
    -0.08
    èĶĵ
    -0.08
    esis
    -0.08
    erre
    -0.08
    POSITIVE LOGITS
    ä¾į
    0.09
    .prevent
    0.09
    wij
    0.09
    æļ¹
    0.09
     AttributeSet
    0.08
    DDS
    0.08
    èįł
    0.08
    .dds
    0.08
    _PRI
    0.08
     Prix
    0.08
    Activations Density 0.004%

    No Known Activations