© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52822
    Prev
    Next
    INDEX
    Explanations

    online gambling and games

    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
    èIJģ
    -0.09
    çķĪ
    -0.09
     mime
    -0.09
    èİŀ
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
    è¹ĩ
    -0.09
    秣æĪ¿
    -0.09
    æ¼ķ
    -0.08
    æİĴæ¯Ĵ
    -0.08
    è¿ĽåŁİ
    -0.08
    POSITIVE LOGITS
     game
    0.09
    廳
    0.09
     sweeps
    0.09
     Players
    0.09
     Sweep
    0.08
    èĥ´
    0.08
    çݩ家
    0.08
    çļĦ游æĪı
    0.08
    /games
    0.08
    åĬ¿åĬĽ
    0.08
    Activations Density 0.166%

    No Known Activations