© 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. 37252
    Prev
    Next
    INDEX
    Explanations

    predict that

    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
     Dal
    -0.10
    ologically
    -0.09
    å¡ĺ
    -0.09
     recl
    -0.09
    å½ĵä¹ĭ
    -0.08
    ipt
    -0.08
    è¿ĻçĤ¹
    -0.08
    缮çļĦåľ¨äºİ
    -0.08
    éĢ¡
    -0.08
     بذÙĦÙĥ
    -0.08
    POSITIVE LOGITS
    çľĭäºĨä¸Ģ
    0.09
    å¾Ģ
    0.09
    isky
    0.09
    æĭ¿åĩº
    0.09
    人们对
    0.09
    ادÙĬ
    0.09
    åīĬå¼±
    0.09
    åĨĽå®ĺ
    0.08
    æŀĿ
    0.08
    æ¯ıå¹´éĥ½
    0.08
    Activations Density 0.051%

    No Known Activations