© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52739
    Prev
    Next
    INDEX
    Explanations

    second chance opportunity alarm alert dawn

    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
    czy
    -0.10
    è·Ĺ
    -0.09
     kênh
    -0.09
    å¸Ľ
    -0.09
     Karn
    -0.09
    宫
    -0.09
     niên
    -0.09
    леп
    -0.08
    ähr
    -0.08
    离
    -0.08
    POSITIVE LOGITS
    æľºä¼ļ
    0.12
    èıĩ
    0.10
    éĻª
    0.10
    麻
    0.09
    æľºéģĩ
    0.09
    缨
    0.09
    è¦ģ好好
    0.09
    æ©Łæľĥ
    0.09
    æīĺ
    0.09
    çļĦæľºä¼ļ
    0.09
    Activations Density 0.071%

    No Known Activations