© 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. 627
    Prev
    Next
    INDEX
    Explanations

    Highland links, book panel, rock concert

    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
    æ·¹
    -0.10
     legally
    -0.09
    pyx
    -0.09
    éĩĩ访
    -0.09
    åľ¨åĨħçļĦ
    -0.09
    åı«
    -0.08
    brace
    -0.08
    PURE
    -0.08
    opause
    -0.08
    KL
    -0.08
    POSITIVE LOGITS
    éĤ£ç§į
    0.15
    åºĶæľīçļĦ
    0.13
    çļĦéĤ£ç§į
    0.12
    åħ¸åŀĭ
    0.11
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.10
    åĩłåĪĨ
    0.10
    常è§ģ
    0.09
    ç«Ļéķ¿
    0.09
    algo
    0.09
    æĥ¯
    0.09
    Activations Density 0.081%

    No Known Activations