© 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. 20500
    Prev
    Next
    INDEX
    Explanations

    social media posts and 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
    éĿ¢åŃĶ
    -0.09
    èijµ
    -0.09
    å¹³éĿĻ
    -0.09
    æĺŁçº§éħĴåºĹ
    -0.09
    æĸ°åĬ¨èĥ½
    -0.09
    èĢģåŃĹåı·
    -0.08
    æ´Ļ
    -0.08
    onga
    -0.08
     Tutor
    -0.08
    èĬĿ麻
    -0.08
    POSITIVE LOGITS
     posts
    0.10
    é¢ľ
    0.10
    å±ij
    0.09
    posts
    0.09
    åĦ¿
    0.09
    /posts
    0.09
    IDO
    0.09
    æĬµ
    0.09
    çĤİ
    0.08
    éĴĹ
    0.08
    Activations Density 0.112%

    No Known Activations