© 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. 20895
    Prev
    Next
    INDEX
    Explanations

    going for

    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
     Gem
    -0.09
     Pand
    -0.09
     hell
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    ำ
    -0.08
    åIJIJ
    -0.08
    ä¸Ģå¤ľ
    -0.08
     Kee
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    移åĬ¨ç«¯
    -0.08
    POSITIVE LOGITS
    æŀŀ
    0.10
    èĹı
    0.09
    ãģĹãĤĩãģĨ
    0.09
    ãģĿãĤĮãģ«
    0.09
    æĢª
    0.09
    ç¹ģçIJIJ
    0.09
    è¸Ĭè·ĥ
    0.09
    æºľ
    0.09
    iente
    0.08
    京éĥ½
    0.08
    Activations Density 0.029%

    No Known Activations