© 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. 20494
    Prev
    Next
    INDEX
    Explanations

    colors and political/religious affiliations

    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
    é§IJ
    -0.09
     Fletcher
    -0.09
    gregate
    -0.08
    azioni
    -0.08
    ynamo
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    çīĪæĿĥ声æĺİ
    -0.08
    eat
    -0.08
    Rub
    -0.08
    壮
    -0.08
    POSITIVE LOGITS
    çĶļ
    0.09
    ä¹ĥèĩ³
    0.09
    çļĦå¿ĥæĥħ
    0.08
    ฯ
    0.08
    ãģªãĤĭ
    0.08
    æĶ¯æĮģåĬĽåº¦
    0.08
    å¥ĭæĸĹ缮æłĩ
    0.08
    ä¼ĹæīĢ
    0.08
    äºŁ
    0.08
    çŁŃ缺
    0.08
    Activations Density 0.442%

    No Known Activations