© 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. 9299
    Prev
    Next
    INDEX
    Explanations

    consecutive streak or row

    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
    tap
    -0.10
    apsed
    -0.09
    ilst
    -0.09
    Dot
    -0.09
    idot
    -0.08
    Enlarge
    -0.08
    ä¸ĭæīĭ
    -0.08
     Starter
    -0.08
    dot
    -0.08
    isper
    -0.08
    POSITIVE LOGITS
    åĢļ
    0.10
     overall
    0.10
    ä¸įåħĭ
    0.10
    大大å°ıå°ı
    0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    0.10
    åıĺåİĭ
    0.09
    æĸĩåĮĸ产ä¸ļ
    0.09
     Overall
    0.09
    ä¼
    0.09
    磨
    0.09
    Activations Density 0.041%

    No Known Activations