© 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. 8503
    Prev
    Next
    INDEX
    Explanations

    finished, lost, with, of

    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
    çŀŃ解並
    -0.09
    éªĤ
    -0.09
    æĦ£
    -0.08
     gig
    -0.08
    .appspot
    -0.08
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.08
    åĨ¬å¥¥ä¼ļ
    -0.08
    å¿ĺ
    -0.08
    pub
    -0.08
    IFS
    -0.08
    POSITIVE LOGITS
    ä½ľåĵģåĨħ容
    0.09
    æľ¬æ¬¡
    0.09
    çľģåĨħ
    0.09
    åĿĩ为
    0.08
    æŶéļĶ
    0.08
    è¯
    0.08
    该项
    0.08
     cyl
    0.08
    æĢ»éĺŁ
    0.08
    两项
    0.08
    Activations Density 0.109%

    No Known Activations