© 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. 7013
    Prev
    Next
    INDEX
    Explanations

    corporation or company

    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
    å¾ĹæĦı
    -0.11
    çĪ¶åŃIJ
    -0.09
    ä¾Ķ
    -0.09
    åħ³äºİæĪij们
    -0.09
    rose
    -0.09
    éĻ²
    -0.09
    è±ĨæµĨ
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    ä¸įæĩĤ
    -0.08
    ioned
    -0.08
    POSITIVE LOGITS
    åĴĮ个人
    0.09
    æĢ§è´¨
    0.09
    -kit
    0.09
    欲
    0.09
    ubber
    0.09
    ç±»åŀĭçļĦ
    0.09
    ISTS
    0.08
    -type
    0.08
    å½¢å¼ı
    0.08
    åĩºç§Łè½¦
    0.08
    Activations Density 0.068%

    No Known Activations