© 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. 36783
    Prev
    Next
    INDEX
    Explanations

    flow of fluids, steam, pipe applications

    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
    æĢ»ä½ĵè§ĦåĪĴ
    -0.09
    饿
    -0.09
    ocom
    -0.09
    éĻŁ
    -0.09
    è¡Į车
    -0.09
    å°ļ
    -0.09
    åIJ¬å®Į
    -0.09
    çķľçī§
    -0.09
     Garland
    -0.09
    _asc
    -0.08
    POSITIVE LOGITS
    æµģéĩı
    0.12
     flow
    0.10
     Flow
    0.10
    Flow
    0.10
    å¾Ĺ罪
    0.10
    éķ¯
    0.10
    .flow
    0.09
    _flow
    0.08
    åIJĦå¼ıåIJĦæł·
    0.08
    被æįķ
    0.08
    Activations Density 0.084%

    No Known Activations