© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38078
    Prev
    Next
    INDEX
    Explanations

    composer, writer, or educator after mentioning place names

    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
    æįŀ
    -0.09
    éĹ¾
    -0.09
    ouns
    -0.09
    æĭĽåij¼
    -0.08
    å¿ĥæĢĿ
    -0.08
    å°ıé¢Ŀ
    -0.08
    åįķ车
    -0.08
    辩论
    -0.08
    à¸Ńà¸ģ
    -0.08
    éĹ®éģĵ
    -0.08
    POSITIVE LOGITS
    æ¼Ķå¥ı
    0.17
    ä¹IJåĻ¨
    0.13
    éŁ³ä¹IJ
    0.12
    éŁ³ä¹IJä¼ļ
    0.12
    æ¼Ķåĩº
    0.12
    åĶ±çīĩ
    0.10
    弦
    0.10
    表æ¼Ķ
    0.10
    ertoire
    0.10
     Music
    0.10
    Activations Density 0.254%

    No Known Activations