© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37425
    Prev
    Next
    INDEX
    Explanations

    nursing and nursing homes

    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
    ä¸įäºĨ
    -0.11
    tern
    -0.09
    åĴİ
    -0.09
     khỼp
    -0.08
    é¢ı
    -0.08
    isp
    -0.08
    è°¤
    -0.08
    odor
    -0.08
    uster
    -0.08
    anche
    -0.08
    POSITIVE LOGITS
    maid
    0.19
    maids
    0.14
    folk
    0.10
    esis
    0.10
    felt
    0.10
    çĶ¨åĵģ
    0.10
    esian
    0.10
    woman
    0.10
    aceutical
    0.09
    ingly
    0.09
    Activations Density 0.012%

    No Known Activations