© 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. 26126
    Prev
    Next
    INDEX
    Explanations

    actions after "you" or "your"

    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
    å¹½
    -0.11
    ç§ī
    -0.10
    å°Ŀ
    -0.09
    æŃ¢
    -0.09
    好å¥ĩ
    -0.09
    æĦŁåħ´è¶£
    -0.08
    æ»´
    -0.08
    iards
    -0.08
    aes
    -0.08
    uta
    -0.08
    POSITIVE LOGITS
    让æĪij
    0.16
    ç»ĻæĪij
    0.15
    æĺ¯æĪij
    0.15
    æĺ¯æĪijçļĦ
    0.15
    éĹ®æĪij
    0.15
    对æĪij说
    0.15
    è·ŁæĪij说
    0.15
     me
    0.15
     мне
    0.15
    äºĨæĪijçļĦ
    0.14
    Activations Density 0.592%

    No Known Activations