© 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. 8173
    Prev
    Next
    INDEX
    Explanations

    copyright notice or author names

    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
    èİ·å¾ĹæĦŁ
    -0.15
    èµĭèĥ½
    -0.15
    åįģä¹Ŀ大
    -0.15
    åĬłæĮģ
    -0.14
    åħ¬ä¼Ĺåı·
    -0.14
    åħļçļĦåįģä¹Ŀ
    -0.14
    åĪĿå¿ĥ
    -0.13
    ä¸įå¿ĺåĪĿå¿ĥ
    -0.13
    åįģåĽĽäºĶ
    -0.13
    æĬĸéŁ³
    -0.13
    POSITIVE LOGITS
    éĩijèŀįåį±æľº
    0.17
    ç»ĻåĬĽ
    0.15
     iPod
    0.14
    ç§ijåѦåıijå±ķ
    0.14
    汶å·Ŀ
    0.14
    奥巴马
    0.13
    åįģäºĮäºĶ
    0.13
    åıĪ好åıĪå¿«
    0.13
    æĸ°åĨľæĿij
    0.13
     Flickr
    0.11
    Activations Density 0.401%

    No Known Activations