© 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. 58185
    Prev
    Next
    INDEX
    Explanations

    laid or lay followed by an adverb

    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
    éĶ¢
    -0.10
    ëĿ¼ëıĦ
    -0.10
    iler
    -0.10
    nels
    -0.09
    åľ¨æĪijçľĭæĿ¥
    -0.09
    æģĻ
    -0.09
    ය
    -0.09
    éļĶçĿĢ
    -0.09
    -gray
    -0.09
    sty
    -0.09
    POSITIVE LOGITS
    工夫
    0.12
    åĬŁå¤«
    0.11
    ings
    0.11
    çħ
    0.10
    áºŃn
    0.10
    ters
    0.09
    mates
    0.09
    enschaft
    0.09
    backs
    0.09
    tn
    0.09
    Activations Density 0.014%

    No Known Activations