© 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. 35780
    Prev
    Next
    INDEX
    Explanations

    sepsis

    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
    说æľį
    -0.10
    éĩįå¤į
    -0.09
    硬度
    -0.09
     dicks
    -0.09
    æݺ
    -0.09
    éĴĹ
    -0.09
    ields
    -0.08
    ä¹ĺ车
    -0.08
    èµį
    -0.08
    æij©æĵ¦
    -0.08
    POSITIVE LOGITS
    åIJ¯
    0.10
    æ¶ĪçģŃ
    0.09
    ä½ĵ系建设
    0.09
    èħ¾é£ŀ
    0.09
     lift
    0.09
    æĬ¬
    0.09
    liers
    0.08
     Chairman
    0.08
    çݰ代åĮĸ
    0.08
    åķŁ
    0.08
    Activations Density 0.236%

    No Known Activations