© 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. 52317
    Prev
    Next
    INDEX
    Explanations

    posts and social media updates

    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
    éĹ»
    -0.12
    ä½łèĩªå·±
    -0.10
    大è¡Ĺ
    -0.10
     ниÑĩ
    -0.10
    åĪ¤
    -0.10
    çħ§æł·
    -0.09
    åµ´
    -0.09
     Pleasant
    -0.09
    èģŀ
    -0.09
    åIJ¬åĪ°
    -0.09
    POSITIVE LOGITS
    åĨĻéģĵ
    0.13
    çĸijä¼¼
    0.11
    ç²īä¸Ŀ
    0.10
    åĽ¾æĸĩ
    0.10
    æľīç½ijåıĭ
    0.09
    å¸ĸåŃIJ
    0.09
    æĬĬèĩªå·±çļĦ
    0.09
    è¿·æĥij
    0.09
    éħįæľī
    0.09
    说èĩªå·±
    0.09
    Activations Density 0.053%

    No Known Activations