© 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. 57573
    Prev
    Next
    INDEX
    Explanations

    nasopharyngeal carcinoma

    np_acts-logits-general · gemini-2.5-flash-lite

    medical and biomedical terms—diseases, anatomical sites, proteins, pathogens, and related clinical/pathology vocabulary.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
     $\
    -0.05
     Arg
    -0.05
     temper
    -0.04
    éĽĩ主
    -0.04
     TR
    -0.04
    åĵªæĢķæĺ¯
    -0.04
    (agent
    -0.03
    _tests
    -0.03
    Ruby
    -0.03
    cri
    -0.03
    POSITIVE LOGITS
     JP
    0.04
    强åĬĽ
    0.04
    å±ł
    0.04
    åĩ¶æīĭ
    0.04
    ç²³
    0.04
    åģ·åģ·
    0.04
     particip
    0.04
    qual
    0.04
    éĽĦåİļ
    0.04
    @@@@
    0.04
    Activations Density 49.338%

    No Known Activations