© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61378
    Prev
    Next
    INDEX
    Explanations

    legal documents and wills

    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
    è¤Ĭ
    -0.10
    åħĢ
    -0.09
    åĩĢ
    -0.09
    åĩĢåľŁ
    -0.09
    éĢļæĬ¥
    -0.09
    ǵ
    -0.09
     gros
    -0.09
    ç§ĥ
    -0.09
    ä¹į
    -0.09
    ä¾Ī
    -0.09
    POSITIVE LOGITS
    äºĨä¸Ģ份
    0.11
    éģĹ
    0.10
    ä¸Ģ份
    0.09
    ç«ĭ
    0.09
    æĦ¿æľĽ
    0.09
     wishes
    0.09
    åĺ±
    0.09
    åīįçŀ»æĢ§
    0.09
    èĩªæĦ¿
    0.09
    ãģĹãģ¦ãģĬãģı
    0.09
    Activations Density 0.094%

    No Known Activations