© 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. 39183
    Prev
    Next
    INDEX
    Explanations

    year’s

    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
    AndUpdate
    -0.11
    ä½Ļ人
    -0.09
    æį»
    -0.09
    éĺŁåijĺ们
    -0.08
    éļħ
    -0.08
    аÑħ
    -0.08
    èįª
    -0.08
    uss
    -0.08
    urt
    -0.08
    onis
    -0.08
    POSITIVE LOGITS
    çļĦæĪIJåĬŁ
    0.13
    çļĦ
    0.13
    çļĦå°ı
    0.13
    çļĦè®°å¿Ĩ
    0.13
    çļĦç²¾ç¥ŀ
    0.13
    çļĦä¼ģä¸ļ
    0.12
    çļĦå¿ĥ
    0.12
    çļĦåŃ¦ä¹ł
    0.12
    çļĦçľ¼
    0.12
    ’s
    0.12
    Activations Density 0.022%

    No Known Activations