© 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. 57576
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    åĴĮå®ĮåĸĦ
    -0.10
    fern
    -0.10
    ENTE
    -0.10
    åĴĮ社ä¼ļ
    -0.10
    æĢ§åĴĮ
    -0.09
    åĴĮåħ¶ä»ĸ
    -0.09
    è´¨éĩıåĴĮ
    -0.09
    建设åĴĮ
    -0.08
    çIJĨ解åĴĮ
    -0.08
     Fortune
    -0.08
    POSITIVE LOGITS
    åIJĦæł·
    0.10
    åĪĽæĸ°èĥ½åĬĽ
    0.09
    佬
    0.08
    ock
    0.08
    家ä¼Ļ
    0.08
    åIJĦ级
    0.08
    /or
    0.08
    诸
    0.08
    å¯Ĩçłģ
    0.08
    å·§
    0.07
    Activations Density 0.413%

    No Known Activations