© 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. 21183
    Prev
    Next
    INDEX
    Explanations

    saving things

    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
    åIJĮç±»
    -0.10
    诫
    -0.09
    needle
    -0.09
    oyer
    -0.09
    stricted
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    çŁ¥éģĵèĩªå·±
    -0.08
    家å±ħ
    -0.08
    åĽ¾æĸĩ
    -0.08
    .wrapper
    -0.08
    POSITIVE LOGITS
    ä½ıäºĨ
    0.10
    空ä¸Ń
    0.09
    æĮ½åĽŀ
    0.09
    olla
    0.09
    åģļåĩºäºĨ
    0.08
    Bot
    0.08
    å°ı康社ä¼ļ
    0.08
    olic
    0.08
    æģ¢å¤įæŃ£å¸¸
    0.08
    ERIC
    0.08
    Activations Density 0.013%

    No Known Activations