© 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. 8583
    Prev
    Next
    INDEX
    Explanations

    one of others

    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
    æ¢ĥ
    -0.11
    èµ·æĿ¥äºĨ
    -0.10
    anja
    -0.09
    iment
    -0.09
    anj
    -0.09
    izzer
    -0.08
    ç»·
    -0.08
    pics
    -0.08
    棣
    -0.08
    urat
    -0.08
    POSITIVE LOGITS
     others
    0.17
    others
    0.13
    Others
    0.12
     Others
    0.12
    ä¹Łæľī
    0.11
    åıĪæľī
    0.11
    åħ¶æ¬¡æĺ¯
    0.11
    ä¹Łæľīä¸ĢäºĽ
    0.11
    æľīçļĦ
    0.10
    åħ¶ä»ĸ人
    0.10
    Activations Density 0.222%

    No Known Activations