© 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. 30960
    Prev
    Next
    INDEX
    Explanations

    is/was followed by past participle

    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
    æľ¬èº«
    -0.09
    æ´»å¾Ĺ
    -0.09
    èĩªèº«
    -0.09
    åľ°ä½į
    -0.09
    ptime
    -0.09
     itself
    -0.09
    çļĦåľ°ä½į
    -0.09
    棵
    -0.08
    çļĦåħ·ä½ĵ
    -0.08
    æľ¬èº«çļĦ
    -0.08
    POSITIVE LOGITS
    eon
    0.09
    åľĪ
    0.09
    éŀį
    0.08
    éªĭ
    0.08
    å¾ģ
    0.08
    epy
    0.08
    é¼»åŃIJ
    0.08
    åŃĺåľ¨
    0.08
    ats
    0.08
    resses
    0.08
    Activations Density 0.389%

    No Known Activations