© 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. 37127
    Prev
    Next
    INDEX
    Explanations

    types or categories of people/things

    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
    ENA
    -0.10
    童年
    -0.09
    è¾ħ
    -0.09
    æŀ¶
    -0.09
     lad
    -0.09
     tantal
    -0.09
    CLR
    -0.09
    åŃ©åŃIJ们
    -0.08
     Cousins
    -0.08
     Budd
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īæł·çļĦ
    0.12
    é«ĺç´łè´¨
    0.12
    ãĤ¿ãĤ¤ãĥĹ
    0.12
    人次
    0.11
     PROFILE
    0.11
    士
    0.11
    ä¹ĭ人
    0.10
     profile
    0.10
    ç±»åŀĭçļĦ
    0.10
    人æīį
    0.10
    Activations Density 0.258%

    No Known Activations