© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    time before or later

    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
    娱
    -0.10
     CPS
    -0.09
    æŁ°
    -0.09
    è¢į
    -0.08
    åı¯æĥ³èĢĮ
    -0.08
    å½ĵä¹ĭ
    -0.08
     sever
    -0.08
    cps
    -0.08
    ä¸įçķĻ
    -0.08
    ablo
    -0.08
    POSITIVE LOGITS
    好äºĭ
    0.10
     Extend
    0.09
    åIJĦ大
    0.09
     дела
    0.09
    arily
    0.09
    åĽĽåŃ£
    0.08
    .Exec
    0.08
    olan
    0.08
    extend
    0.08
    åģļ个
    0.08
    Activations Density 0.006%

    No Known Activations