© 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. 22180
    Prev
    Next
    INDEX
    Explanations

    allow people

    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
    åĩłå¼ł
    -0.10
    å¸ĤæķĻèĤ²å±Ģ
    -0.10
    ä»ĸæĺ¯ä¸Ģ个
    -0.10
    çļĦæĪ¿åŃIJ
    -0.10
    è¿Ļé¦ĸæŃĮ
    -0.09
    è¿Ļå¼ł
    -0.09
    对ä»ĸ们
    -0.09
    ä»ĸæĺ¯
    -0.09
    çļĦæľĭåıĭ
    -0.09
    cola
    -0.09
    POSITIVE LOGITS
    人们
    0.24
    人åĢij
    0.17
     people
    0.17
    çĶ¨æĪ·
    0.17
    大家
    0.14
     users
    0.14
    广大
    0.14
    人们çļĦ
    0.14
    èĢĥçĶŁ
    0.14
     полÑĮзоваÑĤ
    0.14
    Activations Density 0.255%

    No Known Activations