© 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. 37055
    Prev
    Next
    INDEX
    Explanations

    husband or wife

    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
    ons
    -0.09
    çŁ³æ¦´
    -0.09
    blick
    -0.09
    å¯Ħæīĺ
    -0.09
    cloud
    -0.08
    äºij端
    -0.08
     NOM
    -0.08
    幺
    -0.08
    bow
    -0.08
    èIJ½
    -0.08
    POSITIVE LOGITS
    eneg
    0.11
    强åĬĽ
    0.11
    artment
    0.10
    ä¸Ģ人
    0.10
    æ¼ł
    0.10
    å¹³éĿĻ
    0.10
    æľīçĶ¨
    0.09
    reet
    0.09
    enge
    0.09
    ãĤ¨ãĥįãĥ«
    0.09
    Activations Density 0.038%

    No Known Activations