© 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. 39939
    Prev
    Next
    INDEX
    Explanations

    delivery, business, agile

    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
    æIJ¬è¿ģ
    -0.09
    åħ±åĴĮåĽ½
    -0.09
    ç©°
    -0.09
    ç«ĭå¿Ĺ
    -0.09
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    dispatcher
    -0.09
    ç§įæĹı
    -0.09
    éĢĥçĶŁ
    -0.09
    åѤçĭ¬
    -0.09
    åįķ身
    -0.09
    POSITIVE LOGITS
    交ä»ĺ
    0.12
    ä¸ĢæľŁ
    0.10
    onian
    0.10
    Delivery
    0.09
     delivery
    0.09
    ä¸Ģ段
    0.09
    é¢ijç¹ģ
    0.08
    æĬµ
    0.08
     delivered
    0.08
    注éĩį
    0.08
    Activations Density 0.035%

    No Known Activations