© 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. 37403
    Prev
    Next
    INDEX
    Explanations

    triggering events

    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
    西æ¹ĸ
    -0.10
    unist
    -0.09
    ç´¯äºĨ
    -0.09
    uki
    -0.09
     ÑĤоÑĩно
    -0.09
    -NLS
    -0.09
    ика
    -0.09
    éĿ¢åŃIJ
    -0.09
    arias
    -0.09
    /OR
    -0.09
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.11
    äºĨä¸Ģåľº
    0.10
    edList
    0.10
    ness
    0.10
    åħ±æĮ¯
    0.10
    äºĨ大éĩıçļĦ
    0.10
    ä¸Ģç³»åĪĹ
    0.09
    æĢ§å¼º
    0.09
    oud
    0.09
    æĸ°ä¸Ģè½®
    0.09
    Activations Density 0.032%

    No Known Activations