© 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. 51814
    Prev
    Next
    INDEX
    Explanations

    oil refining and production processes

    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
    åľ¨èģĮ
    -0.09
    è¾ĺ
    -0.09
    æĴĴ
    -0.09
    æ¶Ī失äºĨ
    -0.08
    èī¯å¿ĥ
    -0.08
    åĽĽæĸ¹
    -0.08
    forme
    -0.08
    åĨ·åºĵ
    -0.08
    hee
    -0.08
    èĺ¸
    -0.08
    POSITIVE LOGITS
    çĶŁæĹ¥
    0.10
    erten
    0.10
    豺
    0.09
     nú
    0.09
     CWE
    0.09
    辫
    0.09
    æŁ¥çľĭåħ¨æĸĩ
    0.09
     ÐĴлад
    0.09
    è§Ħ模æľĢ大
    0.09
    产åĵģç»ıçIJĨ
    0.09
    Activations Density 0.069%

    No Known Activations