© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18650
    Prev
    Next
    INDEX
    Explanations

    eat or consume

    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
    hel
    -0.09
    presso
    -0.09
     heav
    -0.09
     tether
    -0.09
    éķ¿éķ¿
    -0.08
    èĩªä¸»
    -0.08
     strateg
    -0.08
    çıµ
    -0.08
     extraction
    -0.08
    åıĹçĽĬ
    -0.08
    POSITIVE LOGITS
    æİīäºĨ
    0.11
     swallowed
    0.10
    åIJŀ
    0.10
    æİī
    0.10
    æĿĤ
    0.10
    åIJŀåĻ¬
    0.09
    åķ®
    0.09
    ÙĦات
    0.09
    åIJĥå¾Ĺ
    0.09
    æ®Ĩ
    0.09
    Activations Density 0.020%

    No Known Activations