© 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. 51762
    Prev
    Next
    INDEX
    Explanations

    burger and related words

    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
    ç»ļ丽
    -0.09
    ê»ı
    -0.09
    æ¿¡
    -0.09
    èݼ
    -0.09
    illé
    -0.09
    ugin
    -0.08
    illet
    -0.08
    azel
    -0.08
    -do
    -0.08
    aphore
    -0.08
    POSITIVE LOGITS
    iest
    0.09
    大家åĪĨ享
    0.09
    enal
    0.09
    éĻ´
    0.08
    inal
    0.08
    zos
    0.08
    inton
    0.08
    inating
    0.08
    inated
    0.08
    inals
    0.08
    Activations Density 0.004%

    No Known Activations