© 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. 8002
    Prev
    Next
    INDEX
    Explanations

    actions or decisions made

    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
    åIJĦèĩª
    -0.11
    åIJĦèĩªçļĦ
    -0.10
    ä¼´éļı
    -0.09
     boyc
    -0.09
     eds
    -0.08
    äºī缸
    -0.08
    åħ¬è®¤
    -0.08
    主人
    -0.08
    éĤª
    -0.08
    é¾ĩ
    -0.08
    POSITIVE LOGITS
    亲èĩª
    0.24
     himself
    0.20
    ä¸ĭ令
    0.17
    带é¢Ĩ
    0.17
     personally
    0.17
    åĴĮä»ĸçļĦ
    0.16
     Himself
    0.15
    ä¸ĭè¾¾
    0.14
    çİĩé¢Ĩ
    0.14
    麾
    0.14
    Activations Density 0.204%

    No Known Activations