© 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. 52009
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by descriptions

    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
    å½ĵäºĭ
    -0.09
    ä¸Ńæľī
    -0.08
    quan
    -0.08
    ç»Ĵ
    -0.08
    facet
    -0.08
     nghĩa
    -0.08
    涣
    -0.08
     bá»ģ
    -0.08
    åŀĤ
    -0.08
    çļĦè¶ĭåĬ¿
    -0.08
    POSITIVE LOGITS
    åij
    0.08
    çŁ¢
    0.08
    äºĮæľŁ
    0.08
    ìį¨
    0.08
    赶快
    0.08
    ä¸įçŁ¥
    0.08
    çĻ¾å®¶
    0.08
    å¾Īéĩįè¦ģ
    0.08
    jer
    0.08
    sWith
    0.08
    Activations Density 0.192%

    No Known Activations