© 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. 19713
    Prev
    Next
    INDEX
    Explanations

    intrigue, plotting, power, ambition, study

    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
    æİı
    -0.10
    è¿ĺä¸įéĶĻ
    -0.10
    lint
    -0.09
    çļĦç¾İ好
    -0.09
    è´Łæĭħ
    -0.09
    æĪĨ
    -0.09
    æĤ¦
    -0.09
    æĢĢæĬ±
    -0.09
    åŀĥ
    -0.08
    éļħ
    -0.08
    POSITIVE LOGITS
    ç«ŀäºī
    0.13
    çŃĸçķ¥
    0.13
    è°ĭ
    0.13
    æĶ¿æ²»
    0.12
    éĺ´è°ĭ
    0.12
     Mach
    0.12
    æīĭèħķ
    0.11
    æĿĥåĬĽ
    0.11
    çŃ¹çłģ
    0.11
    宫廷
    0.11
    Activations Density 0.089%

    No Known Activations