© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8553
    Prev
    Next
    INDEX
    Explanations

    with a / have a

    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
    天çĶŁ
    -0.10
     пÑĢежде
    -0.09
    é̏
    -0.09
    罩
    -0.09
    åĮ»åĬ¡
    -0.09
    дÑĥÑĤ
    -0.09
    èģĮä¸ļæĬĢæľ¯
    -0.09
     Incoming
    -0.09
    ffic
    -0.09
    åģļä¸įåΰ
    -0.09
    POSITIVE LOGITS
     ready
    0.11
    çļĦä¿¡å¿ĥ
    0.10
     useless
    0.09
    éļ¾é¢ĺ
    0.09
     Ready
    0.09
    ready
    0.09
    满满çļĦ
    0.09
     READY
    0.09
    主人åħ¬
    0.09
     newfound
    0.09
    Activations Density 0.122%

    No Known Activations