© 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. 8948
    Prev
    Next
    INDEX
    Explanations

    stopping, had, soon

    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
     пÑĢоб
    -0.10
    åĪĨåĮĸ
    -0.10
    诱æĥij
    -0.08
    illus
    -0.08
    åı£å¾Ħ
    -0.08
    ç»ĵæŀĦè°ĥæķ´
    -0.08
    (JS
    -0.08
    èĢĹ
    -0.08
    æħµ
    -0.08
    insky
    -0.08
    POSITIVE LOGITS
    äºĭåIJİ
    0.13
    第äºĮ天
    0.12
    第ä¸ĢæŶéĹ´
    0.12
    å½ĵæĻļ
    0.12
    马ä¸Ĭ
    0.12
    ç«ĭåį³
    0.12
    ç«ĭåĪ»
    0.11
    伤åı£
    0.11
     immediately
    0.11
    å¿ĥçĸ¼
    0.11
    Activations Density 0.119%

    No Known Activations