© 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. 20382
    Prev
    Next
    INDEX
    Explanations

    highs, $, Canada, decimal places

    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
    é£ŀè·ĥ
    -0.10
    allet
    -0.09
    çĥĪ
    -0.09
    亢
    -0.09
    еÑĩ
    -0.09
    æł·åŃIJ
    -0.09
    çļĦç¼ĺ
    -0.09
    hoff
    -0.09
    ç²¾ç¥ŀæĸĩæĺİ
    -0.08
    ancode
    -0.08
    POSITIVE LOGITS
    ãģįãĤĮãģĦ
    0.08
     иÑģÑĤоÑĢ
    0.08
    ä¸Ľä¹¦
    0.08
    oi
    0.08
    ä¸Ĭæĸ¹
    0.08
     tslib
    0.08
    äºī夺
    0.08
    ç»Ĵ
    0.08
    å¤ļéĩį
    0.08
    lineno
    0.08
    Activations Density 0.022%

    No Known Activations