© 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. 51864
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    侥幸
    -0.08
    æĺŁåº§
    -0.08
     podcasts
    -0.08
    说æĪij
    -0.08
    ä¸įå°ıçļĦ
    -0.08
    åı®
    -0.08
    妨
    -0.08
    rophy
    -0.07
    è¾ĵéĢģ
    -0.07
    èĮķ
    -0.07
    POSITIVE LOGITS
    evento
    0.11
    ãĤ¤ãĥĻãĥ³ãĥĪ
    0.11
    æ´»åĬ¨çİ°åľº
    0.11
     меÑĢопÑĢи
    0.10
    å½ĵ天
    0.10
    åħµåĻ¨
    0.10
    çİ°åľº
    0.10
    éħ©
    0.10
    çİ©èĢį
    0.10
    ourcing
    0.10
    Activations Density 0.045%

    No Known Activations