© 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. 36921
    Prev
    Next
    INDEX
    Explanations

    Patrick and last names

    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
    ears
    -0.11
    รà¸Ń
    -0.10
    aga
    -0.10
    管å§Ķä¼ļ
    -0.10
    structor
    -0.10
    igator
    -0.10
    hardt
    -0.10
    à¹Ģà¸ĩ
    -0.10
    еннÑĥÑİ
    -0.09
    æįĭ
    -0.09
    POSITIVE LOGITS
    ting
    0.11
    ively
    0.10
    ities
    0.09
    hev
    0.09
    rypton
    0.09
    son
    0.09
    à¸ķà¸Ļ
    0.08
    YPE
    0.08
    umbo
    0.08
    encies
    0.08
    Activations Density 0.008%

    No Known Activations