© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    the followed by noun/adjective

    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
    æľīçĿĢ
    -0.10
    èĬ®
    -0.09
    èį©
    -0.09
    æĶĺ
    -0.09
    å®ŀè·µä¸Ń
    -0.09
    羣æŃ£
    -0.09
    ä¸Ģå¹´
    -0.08
    ä¸Ģå°ı
    -0.08
    åı¦æľī
    -0.08
    æľīæŶåĢĻ
    -0.08
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.10
    standing
    0.10
    å¾Ī好çļĦ
    0.09
    /do
    0.09
    oop
    0.09
    å¾Īé«ĺçļĦ
    0.09
     пÑĢаво
    0.09
    åīįéĢĶ
    0.09
    太å¤ļçļĦ
    0.09
    äºĨä¸Ģ份
    0.09
    Activations Density 0.041%

    No Known Activations