© 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. 52332
    Prev
    Next
    INDEX
    Explanations

    common symptoms

    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
    æĭIJ
    -0.09
     Fallen
    -0.09
    4
    -0.08
     Rosenstein
    -0.08
    zym
    -0.08
    åIJĬ
    -0.08
    éĢĤå½ĵ
    -0.08
    -Pack
    -0.08
    ytt
    -0.08
     Äijóng
    -0.08
    POSITIVE LOGITS
    åݲ
    0.11
    åİī害
    0.11
    ç¥ī
    0.10
    åħ¸åŀĭ
    0.10
    åħ¸åŀĭçļĦ
    0.09
    æľīæľŁ
    0.09
    æĬ¥éģĵ
    0.09
    çįIJ
    0.09
    éªĮ
    0.09
    çŃīçĹĩçĬ¶
    0.09
    Activations Density 0.215%

    No Known Activations