© 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. 8493
    Prev
    Next
    INDEX
    Explanations

    fewer than

    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
    hdr
    -0.10
    åģĮ
    -0.10
    _Method
    -0.09
    èĮ«èĮ«
    -0.09
     MyBase
    -0.08
    å¾Ī好
    -0.08
    -0.08
    åĮ¡
    -0.08
    awa
    -0.08
    жд
    -0.08
    POSITIVE LOGITS
    -than
    0.09
    æĦŁåıĹåĪ°äºĨ
    0.09
     than
    0.09
    Singleton
    0.09
    è¿Ļä¸ĢåĪĩ
    0.08
     Bon
    0.08
    å¤Ļ
    0.08
    éģŃåıĹ
    0.08
     bon
    0.08
    æ¼Ķ
    0.08
    Activations Density 0.071%

    No Known Activations