© 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. 21054
    Prev
    Next
    INDEX
    Explanations

    cooling and cold water

    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
    cular
    -0.09
    ä¹ĭ乡
    -0.09
    æĺİåªļ
    -0.09
    uml
    -0.09
    ãģĵãĤĵ
    -0.08
    èī
    -0.08
    念头
    -0.08
     Hanna
    -0.08
    主èIJ¥
    -0.08
    妹åŃIJ
    -0.08
    POSITIVE LOGITS
    åĨ·åį´
    0.20
     cooling
    0.17
    éĻį温
    0.17
     cooled
    0.15
    Cool
    0.15
    cool
    0.15
     cool
    0.14
    åĩī
    0.13
     Cool
    0.13
     Cooling
    0.13
    Activations Density 0.059%

    No Known Activations