© 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. 48373
    Prev
    Next
    INDEX
    Explanations

    ãģ«ãģ¤ pattern

    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
    æĹ¶æľŁçļĦ
    -0.10
    çļĦåĪ°æĿ¥
    -0.10
    è¿Ļæīįæĺ¯
    -0.10
    æĹ¶æľŁ
    -0.10
    é¢Ļ
    -0.10
    ä¹ĭä¸Ń
    -0.10
    ãĤĪãģĨãģª
    -0.10
    ãģĿãĤĮãģ§ãĤĤ
    -0.09
    ãģ¨ãģĵãĤįãģ§
    -0.09
    è¿ĻéĩĮéĿ¢
    -0.09
    POSITIVE LOGITS
    å°ı康
    0.09
    TURE
    0.09
    eries
    0.09
    ãģ¨ãĤĬãģĤ
    0.09
    yah
    0.09
    çĻ»
    0.08
    åĵ¡
    0.08
    ãģ©ãĤĵãģ©
    0.08
    ä¸Ģä¸Ŀ
    0.08
     ìī½ê²Į
    0.08
    Activations Density 0.035%

    No Known Activations