© 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. 36758
    Prev
    Next
    INDEX
    Explanations

    so followed by completion

    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
    èĩªå¦Ĥ
    -0.09
     slog
    -0.09
     зав
    -0.08
    upro
    -0.08
    enames
    -0.08
    åħ¶æīĢ
    -0.08
    åŁĤ
    -0.08
    åİĨåı²æĸ°
    -0.08
    LAG
    -0.08
    llum
    -0.08
    POSITIVE LOGITS
    建议
    0.09
     tys
    0.09
    ä¸įè§ģ
    0.09
    æĹłåĬ©
    0.09
    æīį
    0.08
    ä¸įåı¯
    0.08
     sweeping
    0.08
    mate
    0.08
    åĢ¡è®®
    0.08
    æīįä¼ļ
    0.08
    Activations Density 0.060%

    No Known Activations