© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8485
    Prev
    Next
    INDEX
    Explanations

    resource for, values may, SDK development, book will, countdown whenever, streets where, Elder Leader, solution we, "hollow, Courses each

    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
    æĭ¿åĩº
    -0.11
    éĤ£ç§į
    -0.10
    æ·±å¤ľ
    -0.09
    缸åħ³åĨħ容
    -0.09
    ä¸Ń央空è°ĥ
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    usercontent
    -0.09
    ä¸ĢæĬ¹
    -0.09
    æ¯ķç«Ł
    -0.09
    éĴ§
    -0.08
    POSITIVE LOGITS
    è¡ĮåĬ¨è®¡åĪĴ
    0.09
    梦
    0.08
    rowsing
    0.08
    æĪį
    0.08
     Valk
    0.08
    个æĢ§åĮĸ
    0.07
    为ä¹ĭ
    0.07
     Mens
    0.07
    ä¹ħ
    0.07
     Shack
    0.07
    Activations Density 0.242%

    No Known Activations