© 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. 20902
    Prev
    Next
    INDEX
    Explanations

    list of open source projects

    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
    uf
    -0.09
    èĪį
    -0.08
    墨
    -0.08
     mq
    -0.08
    åĢĴæĺ¯
    -0.08
    _BREAK
    -0.07
    HEL
    -0.07
    主æĮģ人
    -0.07
    足
    -0.07
    UF
    -0.07
    POSITIVE LOGITS
    å¸ĮæľĽå¤§å®¶
    0.13
    å¸ĮæľĽéĢļè¿ĩ
    0.12
    为大家
    0.11
    è¿Ļæĺ¯æĪij们
    0.10
    ä½ĨæĪij们
    0.10
    è¯ļæĦı
    0.10
    纳åħ¥
    0.10
    为äºĨ让
    0.09
    ä¹Łå¸ĮæľĽ
    0.09
    æĪij们çļĦ
    0.09
    Activations Density 0.088%

    No Known Activations