© 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. 36872
    Prev
    Next
    INDEX
    Explanations

    individual contexts

    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
    å®ŀä½ĵç»ıæµİ
    -0.09
    eneral
    -0.09
    æ¥ļ
    -0.08
    大å¥ĸ
    -0.08
    天çĦ¶
    -0.08
    åŃĹæł·
    -0.08
    天æĸĩ
    -0.08
    à¸Ľà¸ģ
    -0.08
    jsp
    -0.08
    æ¶ĪçģŃ
    -0.08
    POSITIVE LOGITS
     individual
    0.14
    个ä½ĵ
    0.14
    individual
    0.13
    个人
    0.12
    Individual
    0.12
     Individual
    0.11
     individually
    0.11
    åĢĭ人
    0.11
     personal
    0.11
    _individual
    0.10
    Activations Density 0.060%

    No Known Activations