© 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. 33784
    Prev
    Next
    INDEX
    Explanations

    African and American representation

    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
    isers
    -0.09
    åŃķèĤ²
    -0.09
    ä¾Ī
    -0.09
    åīįä¸ĸ
    -0.08
    侪
    -0.08
    çĶŁçĮª
    -0.08
    æķ£æĸĩ
    -0.08
    æ¯ı个人çļĦ
    -0.08
    @mail
    -0.08
     Lv
    -0.08
    POSITIVE LOGITS
     representation
    0.13
     Representation
    0.13
    Representation
    0.12
    _representation
    0.11
    representation
    0.11
     representations
    0.10
     Stout
    0.10
    æŃ£èĥ½éĩı
    0.10
     ëĭ¤ìĸij
    0.10
    æĬ¥éģĵ
    0.10
    Activations Density 0.089%

    No Known Activations