© 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. 62666
    Prev
    Next
    INDEX
    Explanations

    by politicians

    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
    TRACT
    -0.09
    emens
    -0.09
    çĶ¨èĩªå·±çļĦ
    -0.08
    æĺŃ
    -0.08
    ä¹Ķ
    -0.08
    agli
    -0.08
    urat
    -0.08
    大çĨĬçĮ«
    -0.08
    èĤ¡ä¸ľå¤§ä¼ļ
    -0.08
    çĶ·ä¸»è§Ĵ
    -0.08
    POSITIVE LOGITS
    许å¤ļ
    0.11
    ä¸ĢäºĽ
    0.10
    ä¸įå°ij
    0.10
    ä¸Ģè§Ī
    0.09
    oric
    0.09
    好å¤ļ
    0.09
    åij¨åĽ´çļĦ
    0.09
     ë§İìĿĢ
    0.09
     many
    0.09
     numerous
    0.09
    Activations Density 0.064%

    No Known Activations