© 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. 35539
    Prev
    Next
    INDEX
    Explanations

    medical condition, problem, specialty

    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
    å¥ĹæĪ¿
    -0.09
    ä¸Ŀ
    -0.09
    _ctl
    -0.08
    ä½ĵçİ°åĩº
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    çµ²
    -0.08
    amp
    -0.08
    rama
    -0.08
     Vander
    -0.08
    äºķ
    -0.08
    POSITIVE LOGITS
    èĤ¤
    0.10
    å¼Ģåĩº
    0.09
    chio
    0.08
    åŃ©åŃIJçļĦ
    0.08
    alian
    0.08
    OutOf
    0.08
    溥
    0.08
    Ùī
    0.08
    对èĩªå·±
    0.08
    ousel
    0.08
    Activations Density 0.017%

    No Known Activations