© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    for noun

    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
     коÑĤоÑĢаÑı
    -0.09
    atos
    -0.08
    ä¸įåIJĮæĦı
    -0.08
    æ¼Ĥ
    -0.08
    ä¸į容
    -0.08
    çļĦçģµéŃĤ
    -0.08
    å·©åĽº
    -0.08
    èħ´
    -0.08
    mittel
    -0.08
    osas
    -0.08
    POSITIVE LOGITS
    æį¢æĪIJ
    0.16
    èĢĮæĺ¯
    0.14
    æį¢åıĸ
    0.12
    æį¢æĿ¥
    0.11
    å¤ĩ
    0.11
    ä¸ĵ注äºİ
    0.11
    èĢĮåİ»
    0.10
    æĶ¹ä¸º
    0.10
    æĶ¹æĪIJ
    0.10
    _focus
    0.10
    Activations Density 0.041%

    No Known Activations