© 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. 35563
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    æľīåĩłä¸ª
    -0.09
    chy
    -0.08
    å¶Ļ
    -0.08
    pered
    -0.08
    4
    -0.08
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.08
    kus
    -0.08
    3
    -0.07
    nier
    -0.07
    IER
    -0.07
    POSITIVE LOGITS
    åı«åģļ
    0.11
    åľºéĿ¢
    0.10
    称ä¹ĭ为
    0.10
    åIJįåı«
    0.10
    åħ¶æīĢ
    0.10
    æ®ĥ
    0.10
    æĿ¥èĩªäºİ
    0.10
    åİ»çľĭçľĭ
    0.09
    æ¯ħåĬĽ
    0.09
    女åŃ©åŃIJ
    0.09
    Activations Density 1.345%

    No Known Activations