© 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. 8936
    Prev
    Next
    INDEX
    Explanations

    crossing safety and lubrication

    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
    å»Ĭ
    -0.09
    åĪļåĪļ
    -0.09
    仲
    -0.08
    åĪļ
    -0.08
    ray
    -0.08
    pts
    -0.08
    åīĽ
    -0.08
    ä¸Ńæĸ°
    -0.08
    pd
    -0.08
     jus
    -0.08
    POSITIVE LOGITS
    é¾Ħ
    0.10
    寿åij½
    0.09
    ç¼ĺåĪĨ
    0.09
    affle
    0.09
    ä½ľé£İ建设
    0.09
    лив
    0.09
    akov
    0.09
    æĬ¤
    0.09
    ëł¹
    0.09
    à¹Ħà¸Ĥ
    0.09
    Activations Density 0.087%

    No Known Activations