© 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. 24167
    Prev
    Next
    INDEX
    Explanations

    dream come true

    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
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.10
     décid
    -0.10
    æĪĺçķ¥æĢ§
    -0.10
    opus
    -0.09
    æĦıåij³
    -0.09
    ä½İä¼°
    -0.09
    康
    -0.09
    èıĬ
    -0.09
    ä¸ĢäºĮ
    -0.09
    ivet
    -0.09
    POSITIVE LOGITS
     dream
    0.11
    åIJijå¾Ģ
    0.11
    梦
    0.11
    Dream
    0.11
    åĻ©
    0.11
    çļĦ梦æĥ³
    0.10
     dreams
    0.10
    dream
    0.10
    梦æĥ³
    0.10
    梦幻
    0.10
    Activations Density 0.022%

    No Known Activations