© 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. 9294
    Prev
    Next
    INDEX
    Explanations

    Egyptian pharaohs and ancient history

    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
     converse
    -0.09
    ession
    -0.09
    reo
    -0.09
    бл
    -0.09
    ä»ħ代表
    -0.08
    æıŃ
    -0.08
     Toll
    -0.08
     Fat
    -0.08
    岸
    -0.08
    ÙħÙĬÙĦ
    -0.08
    POSITIVE LOGITS
    iphy
    0.10
    好人
    0.09
    æİ·
    0.08
     NONINFRINGEMENT
    0.08
    踩
    0.08
     Riv
    0.08
    поз
    0.08
    mitt
    0.08
     RUNNING
    0.08
    inen
    0.08
    Activations Density 0.021%

    No Known Activations