© 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. 37514
    Prev
    Next
    INDEX
    Explanations

    which plus explanation

    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
    zelf
    -0.09
    å¤Ħå¤Ħ
    -0.09
    縱
    -0.09
    beg
    -0.08
     Welsh
    -0.08
    ients
    -0.08
    è¡Įè´¿
    -0.08
    lü
    -0.08
    [](
    -0.08
     rak
    -0.08
    POSITIVE LOGITS
    æĦıåij³çĿĢ
    0.12
    éļ¾æĢª
    0.12
     знаÑĩиÑĤ
    0.11
    缸åºĶçļĦ
    0.10
    UNK
    0.10
    使åħ¶
    0.10
    æ¯Ķäºļ
    0.10
    æĺ¯ä¸Ģ项
    0.10
    导èĩ´
    0.10
    è¿Ļä¹Łæĺ¯
    0.10
    Activations Density 0.070%

    No Known Activations