© 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. 52052
    Prev
    Next
    INDEX
    Explanations

    come followed by prepositions

    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
    æľīäºĨ
    -0.10
    DEX
    -0.10
    åĻ¤
    -0.09
    éĴĪ
    -0.09
     ÐIJлекÑģан
    -0.09
    æĦŁåıĹåĪ°äºĨ
    -0.09
    çĤĻ
    -0.08
    пÑĢакÑĤик
    -0.08
    ä¿Ĺ
    -0.08
    urai
    -0.08
    POSITIVE LOGITS
    ç¹ģ
    0.09
    azer
    0.09
    edes
    0.09
    åįİ侨
    0.09
    ique
    0.08
    å°Ķæĸ¯
    0.08
    ä¸ŃåİŁ
    0.08
    åŃ³
    0.08
    åĩºæĿ¥
    0.08
    åĮºåĪĨ
    0.08
    Activations Density 0.027%

    No Known Activations