© 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. 20851
    Prev
    Next
    INDEX
    Explanations

    leads to and ended

    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
    ä¸ĢéĹª
    -0.09
    强æľīåĬĽ
    -0.09
    æĮ¡ä½ı
    -0.09
    ê°Ŀ
    -0.08
    ossa
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    è¥Ł
    -0.08
    èĢĺ
    -0.08
     обеÑģп
    -0.08
    ospace
    -0.08
    POSITIVE LOGITS
    éħ¿
    0.10
     cul
    0.09
    åŃķèĤ²
    0.09
    è£Ĥ
    0.09
     leads
    0.09
     resulted
    0.09
     lead
    0.09
    æį¢æĿ¥
    0.08
    è¿Ŀæ³ķ
    0.08
    -pos
    0.08
    Activations Density 0.119%

    No Known Activations