© 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. 21390
    Prev
    Next
    INDEX
    Explanations

    ceremony or journey

    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
    å°Ķæĸ¯
    -0.11
    å¿«æĬ¥
    -0.10
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    æĬ¥ç¤¾
    -0.10
    æķ´ä¸ªäºº
    -0.09
    éŀĺ
    -0.09
    æĹ¶è®¸
    -0.09
    è¹¼
    -0.09
    ç¦ģåĮº
    -0.09
    è¥
    -0.09
    POSITIVE LOGITS
    åıijæĮ¥ä½ľçĶ¨
    0.08
    æµģåĩº
    0.07
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.07
     ren
    0.07
    angen
    0.07
     persist
    0.07
    ä¸ĵéĹ¨ä¸º
    0.07
    ä»ĺ
    0.07
    æºIJäºİ
    0.07
    诲
    0.07
    Activations Density 0.186%

    No Known Activations