© 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. 36782
    Prev
    Next
    INDEX
    Explanations

    having fun

    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
    Gar
    -0.09
    ors
    -0.09
    UES
    -0.09
    outu
    -0.08
    APO
    -0.08
    笼
    -0.08
    {{{
    -0.08
    gar
    -0.08
    inger
    -0.08
    ä¸Ģ线
    -0.08
    POSITIVE LOGITS
     fun
    0.20
    ä¹IJ趣
    0.19
     Fun
    0.15
    æľī趣
    0.15
     FUN
    0.15
    fun
    0.14
    欢ä¹IJ
    0.14
    好çİ©
    0.14
    	fun
    0.14
    çļĦä¹IJ趣
    0.14
    Activations Density 0.064%

    No Known Activations