© 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. 36710
    Prev
    Next
    INDEX
    Explanations

    advice due to, notice, information

    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
    æĹłä¸į
    -0.12
    èĢĮä¸įæĺ¯
    -0.11
    èĢĮéĿŀ
    -0.10
    ä¸įå¾Ĺä¸į
    -0.09
    ä¸įå®ľ
    -0.09
    ä¸įèĪį
    -0.09
    TL
    -0.09
    TT
    -0.08
    ä¸įä»ħ
    -0.08
    æ¹ĺ
    -0.08
    POSITIVE LOGITS
     nor
    0.21
    nor
    0.16
     anymore
    0.16
    ä»»ä½ķä¸Ģ个
    0.15
    ä¸Ŀ毫
    0.14
    èĢĮæĺ¯
    0.14
    ä¹Łä¸įæķ¢
    0.13
    æľīä»»ä½ķ
    0.13
    ä¹Łä¸įä¼ļ
    0.13
     Nor
    0.13
    Activations Density 0.169%

    No Known Activations