© 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. 37140
    Prev
    Next
    INDEX
    Explanations

    Sorry, but something went wrong

    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
    åı¨
    -0.09
    çķĻè¨ĢæĿ¿
    -0.09
    ÑĢÑĥз
    -0.09
    ByPrimaryKey
    -0.08
    举
    -0.08
    -loaded
    -0.08
    çľĭçĶµå½±
    -0.08
    ä¸ĢæĬĬ
    -0.08
    _cpus
    -0.08
    Tester
    -0.08
    POSITIVE LOGITS
    æĸ¹éĿ¢çļĦ
    0.09
    cai
    0.09
    eus
    0.08
    æ¹¾
    0.08
    hed
    0.08
    æ´¾åĩº
    0.08
     Humph
    0.08
    èµĦ
    0.08
    çĭ¬èĩª
    0.08
    åĩºäºİ
    0.08
    Activations Density 0.004%

    No Known Activations