© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50702
    Prev
    Next
    INDEX
    Explanations

    at X p.m

    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
    å½ĵæŶçļĦ
    -0.10
    bul
    -0.08
     Pil
    -0.08
    è¸Į
    -0.08
    éĢļ常
    -0.08
    çĪ¨
    -0.08
    èµ°å¾Ĺ
    -0.08
    åģĩæľŁ
    -0.08
    ä¼ļ议精ç¥ŀ
    -0.08
    çķ¦
    -0.08
    POSITIVE LOGITS
     меÑĢопÑĢи
    0.10
    æįı
    0.09
    æĸ°æĬĢæľ¯
    0.09
     tonight
    0.09
     Ung
    0.09
     yön
    0.08
    讲座
    0.08
    ä»ĬæĻļ
    0.08
    ugar
    0.08
    langs
    0.08
    Activations Density 0.073%

    No Known Activations