© 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. 17465
    Prev
    Next
    INDEX
    Explanations

    use existing functionality

    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¿«æĬ¥
    -0.10
    æĪijçļĦå¿ĥ
    -0.10
    æĪij家
    -0.10
    ä¸Ģåı£æ°Ķ
    -0.09
    æĪĸå¤ļæĪĸå°ij
    -0.09
    æĬķæĶ¾
    -0.09
    赶
    -0.09
    èĢģå¸Ī们
    -0.09
    ä¸Ģ款
    -0.08
    è¯¥é¡¹çĽ®
    -0.08
    POSITIVE LOGITS
    èµĦæºIJä¼ĺåĬ¿
    0.15
    åħħåĪĨåĪ©çĶ¨
    0.14
    çļĦä¼ĺåĬ¿
    0.13
    åıijæĮ¥
    0.12
    çİ°æľī
    0.12
    ä¼ĺåĬ¿
    0.12
     resources
    0.12
    çİ°æľīçļĦ
    0.12
    èµĦæºIJ
    0.11
     existing
    0.11
    Activations Density 0.142%

    No Known Activations