© 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. 33857
    Prev
    Next
    INDEX
    Explanations

    past tense verbs 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
    家éķ¿ä»¬
    -0.10
    _accessible
    -0.10
    èĥĮåIJİçļĦ
    -0.10
    çļĦ妻åŃIJ
    -0.09
    两侧
    -0.09
     marg
    -0.09
    UPI
    -0.09
    [label
    -0.08
     forall
    -0.08
    åĬłæ²¹ç«Ļ
    -0.08
    POSITIVE LOGITS
    é«ĺç´łè´¨
    0.12
    æ¶Įçİ°åĩº
    0.11
    好人
    0.10
    人æīį
    0.10
    ä¸Ģ大æī¹
    0.10
    æľīä¸Ģä½į
    0.10
    太å¤ļ
    0.10
    äºĨä¸Ģæī¹
    0.10
    è¿İæĿ¥äºĨ
    0.10
    æłĭ
    0.09
    Activations Density 0.235%

    No Known Activations