© 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. 1236
    Prev
    Next
    INDEX
    Explanations

    your own, as well

    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
    å®Ŀ鸡
    -0.09
    çļĦæĸ¹å¼ıæĿ¥
    -0.08
    æĤ
    -0.08
    åį´ä¸į
    -0.08
    ãģ¨ãģĻãĤĭ
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    æĭ¿åĩº
    -0.08
    éªł
    -0.08
    éĺ¶æ®µæĢ§
    -0.08
    箫
    -0.08
    POSITIVE LOGITS
    endar
    0.10
     exem
    0.09
    大éĥ¨åĪĨ人
    0.09
    æĪļ
    0.09
    æºIJæºIJ
    0.09
    妹妹
    0.08
    ViewState
    0.08
    头æĿ¡
    0.08
    èĢģçĪ¸
    0.08
    hydrate
    0.08
    Activations Density 0.546%

    No Known Activations