© 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. 36844
    Prev
    Next
    INDEX
    Explanations

    hosted in

    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
    åħ¥çĿ¡
    -0.09
    èĮħ
    -0.09
    /latest
    -0.09
    ä¼ģ
    -0.08
    åĪ°åºķæĺ¯
    -0.08
    æŀģé«ĺ
    -0.08
    AndGet
    -0.08
    éĽĨä½ĵ
    -0.08
    èµĸ以çĶŁåŃĺ
    -0.08
    æİ
    -0.08
    POSITIVE LOGITS
    iola
    0.12
    åħ¶ä»ĸçļĦ
    0.10
    æľ¬æĿ¥å°±
    0.09
    åħ¶ä»ĸ
    0.09
    odon
    0.09
     already
    0.09
    æĭŃ
    0.09
    æĸ°åĨľæĿij
    0.08
    ä¹Łä¸įåı¯èĥ½
    0.08
     ×ij׼
    0.08
    Activations Density 0.651%

    No Known Activations