© 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. 36645
    Prev
    Next
    INDEX
    Explanations

    smell, anaerobic, aerobic, sludge

    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
    ä¸ŃåĽ½åĪ¶éĢł
    -0.09
    åĩĮ
    -0.09
    ä¸įæĥľ
    -0.09
    å¿ĻçĿĢ
    -0.09
    acey
    -0.08
    æĦı大
    -0.08
     dest
    -0.08
    èľĺèĽĽ
    -0.08
    tube
    -0.08
    çĬĢ
    -0.08
    POSITIVE LOGITS
    ä¸įä¼ļæľī
    0.11
    åģ¶
    0.10
     smell
    0.09
    بØŃ
    0.09
    ооÑĢ
    0.09
     yans
    0.08
    ä¼ļæľī
    0.08
    èĩŃ
    0.08
    ickness
    0.08
    lems
    0.08
    Activations Density 0.032%

    No Known Activations