© 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. 50738
    Prev
    Next
    INDEX
    Explanations

    determiners followed by nouns

    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
    erd
    -0.09
    çłĴ
    -0.09
    çļĦçIJĨ解
    -0.08
    çļĦåIJĪä½ľ
    -0.08
    _TM
    -0.08
     Cov
    -0.08
     Kamp
    -0.08
    عÙĬد
    -0.08
    éĽķ
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.10
    .wx
    0.10
    æľĭåıĭ们
    0.10
    èĥ½åģļåĪ°
    0.09
    æīĢéľĢè¦ģçļĦ
    0.09
     Stap
    0.09
    åIJĮåѦ们
    0.09
    æĦıè§ģåıįé¦Ī
    0.09
    æīĢèĥ½
    0.09
    (Filter
    0.09
    Activations Density 0.235%

    No Known Activations