© 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. 36870
    Prev
    Next
    INDEX
    Explanations

    likelihood of being

    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
    太å¤ļçļĦ
    -0.10
    好äºĨ
    -0.09
    åĩºäºĨ
    -0.08
    å¤ļå°ij
    -0.08
    Margins
    -0.08
     Yin
    -0.08
    å¾Īæľī
    -0.08
    yled
    -0.08
    çıī
    -0.08
    pez
    -0.08
    POSITIVE LOGITS
    rox
    0.11
     someday
    0.10
    chter
    0.10
    æĺİæĹ¥
    0.10
    è¿Ļè¾ĪåŃIJ
    0.10
    åľ¨è¿Ļç§į
    0.09
    æĤ£ä¸Ĭ
    0.09
    ç»´
    0.09
    èĥ½åģļåĪ°
    0.09
    èİ·èĥľ
    0.09
    Activations Density 0.127%

    No Known Activations