© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49240
    Prev
    Next
    INDEX
    Explanations

    fireplace, stove, wood burning

    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
    æĹłäºº
    -0.09
     Gro
    -0.09
    mary
    -0.09
    éľĵ
    -0.09
    åľ¨ä¸ŃåĽ½
    -0.09
    arias
    -0.09
     gro
    -0.09
    åīª
    -0.09
    ç³ľ
    -0.08
    æĪIJ为ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
     fireplace
    0.12
    å¼ĢæĶ¯
    0.09
    æ°ijæĹıæĸĩåĮĸ
    0.09
    ä¿Ŀå®Ī
    0.09
    æ°ijä¿Ĺ
    0.08
    类产åĵģ
    0.08
     Fireplace
    0.08
     fountain
    0.08
    峡谷
    0.08
    ä¼łç»ŁæĸĩåĮĸ
    0.08
    Activations Density 0.084%

    No Known Activations