© 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. 8978
    Prev
    Next
    INDEX
    Explanations

    engage/engagement

    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
    aceous
    -0.12
    à¹Į
    -0.10
    .Abstractions
    -0.09
    izer
    -0.09
    оÑģÑĮ
    -0.09
    gre
    -0.09
    夸
    -0.08
    æĭį
    -0.08
    okino
    -0.08
    人人éĥ½
    -0.08
    POSITIVE LOGITS
    able
    0.11
    ments
    0.09
    èĩªå¦Ĥ
    0.09
    ¹
    0.09
    ynamo
    0.09
    å¼ı
    0.09
    èĥĦ
    0.09
    éĺħ读åħ¨æĸĩ
    0.09
    utters
    0.08
    antry
    0.08
    Activations Density 0.013%

    No Known Activations