© 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. 55438
    Prev
    Next
    INDEX
    Explanations

    before or after

    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
    å¢ŀ强äºĨ
    -0.09
    åĵ¨
    -0.08
    ç»ĻäºĨ
    -0.08
    ä¸Ģä¸Ŀ
    -0.08
    ulers
    -0.08
    åłª
    -0.08
    è¡Ļ
    -0.08
    èĿĩ
    -0.08
    鲤
    -0.08
    被
    -0.08
    POSITIVE LOGITS
    æĸ¹åı¯
    0.12
    åį³åı¯
    0.11
    ãĤĴãģĶ
    0.10
    便åı¯
    0.09
    注æĦı
    0.09
    çļĦæľĢä½³
    0.09
    æľ¬åħ¬åı¸
    0.08
    æľĢ好
    0.08
    å·¨
    0.08
    çĵľ
    0.08
    Activations Density 0.056%

    No Known Activations