© 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. 22741
    Prev
    Next
    INDEX
    Explanations

    of interleukin, adiponectin, testosterone, fat, dissolved, trim

    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
    èµ°åIJij
    -0.09
     Hairst
    -0.09
    èħł
    -0.09
    alon
    -0.08
    æľīéĴ±
    -0.08
    羣çļ®
    -0.08
    å¬ĸ
    -0.08
    èµ°
    -0.08
    åģļæ³ķ
    -0.08
    ä¸Ģ身
    -0.08
    POSITIVE LOGITS
     various
    0.11
    æŶéĹ´åĴĮ
    0.10
    æŁIJç§į
    0.10
    è¿Ļ两ç§į
    0.09
    诸å¦Ĥ
    0.09
    çīµæĮĤ
    0.09
    ä¼ĺè´¨çļĦ
    0.09
    /respond
    0.09
    åIJĦç§į
    0.09
    æĬĢæľ¯åĴĮ
    0.08
    Activations Density 0.537%

    No Known Activations