© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    Apocalypse, Red Sea, flood, punishment, torture, judge

    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
    -packages
    -0.09
    æłī
    -0.09
    æł¸å¿ĥåĮº
    -0.08
    èݽ
    -0.08
    reib
    -0.08
    å±ł
    -0.08
    èķ¤
    -0.08
    èĪµ
    -0.08
    æī©å¤§
    -0.08
    æĹ¥æĻļéĹ´
    -0.08
    POSITIVE LOGITS
    indr
    0.10
    bü
    0.10
     Noah
    0.09
    .inv
    0.09
    åĪ°æŶåĢĻ
    0.09
    æĮŁ
    0.09
    第äºĮ次
    0.08
    é«ĺä½İ
    0.08
    sty
    0.08
     اÙĦÙħؤ
    0.08
    Activations Density 0.023%

    No Known Activations