© 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. 8929
    Prev
    Next
    INDEX
    Explanations

    disability condition and treatment

    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¸Ģ个好çļĦ
    -0.10
    è¿Ļç¯ĩ
    -0.10
    ullet
    -0.08
     adj
    -0.08
    adj
    -0.08
    åij
    -0.08
    åĵij
    -0.08
    rst
    -0.08
     Turtle
    -0.08
    å¤į
    -0.08
    POSITIVE LOGITS
    åıĺå½¢
    0.10
    éķIJ
    0.10
    åıªèĥ½
    0.10
    éļľ
    0.09
    lio
    0.09
    ä¸įæĸ¹ä¾¿
    0.09
    çļĦçĭ¬çī¹
    0.09
    ä¸Ģéģĵ
    0.09
    å®īç½®
    0.09
    unable
    0.09
    Activations Density 0.078%

    No Known Activations