© 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. 39870
    Prev
    Next
    INDEX
    Explanations

    indefinite articles (un, una) and subsequent 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
    æĻģ
    -0.10
    åĨµ
    -0.09
    ValuePair
    -0.08
    å±ĭ
    -0.08
    valu
    -0.08
    ä¸ĢäºĽ
    -0.08
     wal
    -0.08
    \Schema
    -0.08
    yz
    -0.07
    zos
    -0.07
    POSITIVE LOGITS
    è¦ģç´§
    0.12
    å°ıå°ıçļĦ
    0.11
    æĦıå¢ĥ
    0.10
    å¾Ī大
    0.10
    å¾Īæĺ¯
    0.10
    ä»Ģä¹Īä¸ľè¥¿
    0.10
    å¾Ī大çļĦ
    0.10
    èī¯
    0.10
    å¾Īæľī
    0.09
    å®īåħ¨ä¿Ŀéļľ
    0.09
    Activations Density 0.142%

    No Known Activations