© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64129
    Prev
    Next
    INDEX
    Explanations

    player career

    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
    Negative Logits
    软
    -0.09
    æijĩ头
    -0.09
    æłħ
    -0.08
    å±±ä¸Ĭ
    -0.08
    è´¢ç»ı
    -0.08
    主åĬŀæĸ¹
    -0.08
    åĨįåĬłä¸Ĭ
    -0.08
    ä¸ĩåĪĨ
    -0.08
    éĻ¡
    -0.07
     pros
    -0.07
    POSITIVE LOGITS
    亲èĩª
    0.17
    ä¸Ģ线
    0.13
    亲
    0.12
    亲身
    0.12
    親
    0.11
    æĺ§
    0.11
     ì§ģìłij
    0.11
    缴æİ¥
    0.11
    åīįåı°
    0.11
    åħ·ä½ĵçļĦ
    0.10
    Activations Density 0.104%

    No Known Activations