© 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. 9193
    Prev
    Next
    INDEX
    Explanations

    theater, server, news, history, VSTS

    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
    åĬ£
    -0.09
    åı°åįĹ
    -0.08
    ç§ijå¹»
    -0.08
    çī©ä¸ļåħ¬åı¸
    -0.08
    enheim
    -0.08
    æľĶ
    -0.08
    æĢ»å±Ģ
    -0.08
    çĩ®
    -0.08
    mant
    -0.08
    že
    -0.08
    POSITIVE LOGITS
    posix
    0.10
    _timeout
    0.10
    æ¯ıéĢ¢
    0.08
    åĸĬ
    0.08
    ãģĤãģŁãĤĬ
    0.08
    æĤł
    0.08
    äºĮç»´
    0.08
     Mold
    0.08
    åľ°éģĵ
    0.08
    å®ļéĩı
    0.08
    Activations Density 0.003%

    No Known Activations