© 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. 21435
    Prev
    Next
    INDEX
    Explanations

    dual boot

    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
    骡
    -0.09
    åĮħ
    -0.08
    ä¾ĿéĿł
    -0.08
    æ¡¡
    -0.08
    æį§
    -0.08
    涨价
    -0.08
    setting
    -0.08
    é¼ĵ
    -0.08
     interns
    -0.08
    丽
    -0.08
    POSITIVE LOGITS
    tru
    0.11
    æł©
    0.10
    ä¸įä¸ĭ
    0.09
    å¯Ĵåģĩ
    0.09
    åľ£è¯ŀèĬĤ
    0.09
     завод
    0.09
    æ·¨
    0.09
    ç«
    0.09
    åģĪ
    0.09
    裸
    0.09
    Activations Density 0.083%

    No Known Activations