© 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. 9034
    Prev
    Next
    INDEX
    Explanations

    will be, will come, will fall, will lead

    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
    likely
    -0.11
     Affero
    -0.10
    å¾Ģå¾Ģ
    -0.09
    åı¯èĥ½åŃĺåľ¨
    -0.09
     likely
    -0.09
     arguably
    -0.09
    åı¯ä»¥è¯´æĺ¯
    -0.09
    ä¸Ģå®ļçļĦ
    -0.09
    åħ¸åŀĭçļĦ
    -0.09
     possibly
    -0.09
    POSITIVE LOGITS
    æĶ¶åĪ°
    0.11
    çİĦ
    0.09
     someday
    0.09
    æĪİ
    0.09
    lion
    0.09
    æī¹éĩı
    0.08
    kur
    0.08
    ä¸Ģäºĭ
    0.08
    ä¸Ģå¦Ĥ
    0.08
     bulk
    0.08
    Activations Density 0.060%

    No Known Activations