© 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. 53929
    Prev
    Next
    INDEX
    Explanations

    minutes or mins

    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
    ä¼Ļ
    -0.12
    ä¸ī天
    -0.11
    ä¸ŃåĽ½çī¹èī²
    -0.10
    æľīçĿĢ
    -0.10
    æĹ¥å¤ľ
    -0.09
    åIJįå½ķ
    -0.09
    dens
    -0.09
     Overnight
    -0.09
     lod
    -0.09
     overnight
    -0.09
    POSITIVE LOGITS
    åįģåĪĨéĴŁ
    0.09
    èIJ¥åķĨçݯå¢ĥ
    0.09
     minutes
    0.09
    åĩłåĪĨéĴŁ
    0.09
     mins
    0.09
    minutes
    0.09
    .minutes
    0.09
     Minutes
    0.09
    åĨħç§ij
    0.09
    æ½¢
    0.08
    Activations Density 0.092%

    No Known Activations