© 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. 22484
    Prev
    Next
    INDEX
    Explanations

    nursing home facility

    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
    èİĺ
    -0.10
    fried
    -0.10
    gens
    -0.09
    uae
    -0.09
    é£ŀè¡Įåijĺ
    -0.09
    åĤ
    -0.09
    åĴ½
    -0.09
    ç´łæĿIJ
    -0.09
    éĩįçĶŁ
    -0.08
    rene
    -0.08
    POSITIVE LOGITS
    寡
    0.10
     institutional
    0.10
    åºĬä½į
    0.10
    çĽijçĭ±
    0.09
     facility
    0.09
    å®īç½®
    0.09
     institution
    0.09
    éŃĤ
    0.09
    åħ¥ä½ı
    0.09
     Institution
    0.09
    Activations Density 0.205%

    No Known Activations