© 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. 11364
    Prev
    Next
    INDEX
    Explanations

    henceforth / hereinafter / hereafter

    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
    andr
    -0.10
    åģľä¸ĭ
    -0.09
    èĢį
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    ingo
    -0.08
     chắn
    -0.08
    ms
    -0.08
    åĬłåĢį
    -0.08
    æļ¨
    -0.08
    ä¸į足以
    -0.08
    POSITIVE LOGITS
    ä»ĬåIJİ
    0.26
    以åIJİ
    0.24
    以å¾Į
    0.21
     future
    0.19
    å¾ĢåIJİ
    0.18
    æľªæĿ¥çļĦ
    0.18
    æľªæĿ¥
    0.18
    æĹ¥åIJİ
    0.17
    future
    0.16
    å°ĨæĿ¥
    0.16
    Activations Density 0.060%

    No Known Activations