© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 35097
    Prev
    Next
    INDEX
    Explanations

    occupations or roles

    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
    管è¾ĸ
    -0.10
    Jur
    -0.09
    æīĵçĮİ
    -0.09
    漫éķ¿çļĦ
    -0.09
    ä¸ĭå±ŀ
    -0.09
    æĹ¨åľ¨
    -0.08
    广éĺĶçļĦ
    -0.08
    uil
    -0.08
    è¿Ļ个è¡Įä¸ļ
    -0.08
    èĵĦ
    -0.08
    POSITIVE LOGITS
    è´Łè´£äºº
    0.13
    ä¸Ńå¿ĥ主任
    0.12
    çļĦä¸Ģåijĺ
    0.12
     spokesperson
    0.10
     representative
    0.10
    é¦ĸä½į
    0.10
    é¢ĺ主
    0.10
    å¤Ħå¤Ħéķ¿
    0.10
    éĥ¨éĥ¨éķ¿
    0.10
    主任
    0.09
    Activations Density 0.260%

    No Known Activations