© 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. 35807
    Prev
    Next
    INDEX
    Explanations

    applied to, show how, evaluate, tested for

    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
    èĤļ
    -0.09
    å¾Īå¤ļæŶåĢĻ
    -0.08
    ^[
    -0.08
    reference
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    æĴĩ
    -0.08
    åİļåİļçļĦ
    -0.08
     ÑģобÑģÑĤвенно
    -0.07
    éĤ£ä¸ªæŶåĢĻ
    -0.07
    sn
    -0.07
    POSITIVE LOGITS
    ricks
    0.09
    æķ´æĶ¹æݪæĸ½
    0.09
    åħįéĻ¤
    0.09
    ãĥ¯ãĥ¼ãĤ¯
    0.09
    عش
    0.09
    ç½ij讯
    0.09
    åĩłçĤ¹
    0.09
    ection
    0.08
     PMID
    0.08
    ç»ıèIJ¥èĮĥåĽ´
    0.08
    Activations Density 2.312%

    No Known Activations