© 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. 34436
    Prev
    Next
    INDEX
    Explanations

    who followed by a verb

    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
    符
    -0.10
    éªı
    -0.09
    é¬ĥ
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.08
    éĩijé¢Ŀ
    -0.08
    éªij士
    -0.08
    举è¡ĮçļĦ
    -0.08
     toJSON
    -0.08
    ä¸ĢåIJį
    -0.08
    å¤Ķ
    -0.08
    POSITIVE LOGITS
    æĭ
    0.09
    .nil
    0.09
    /rs
    0.09
    adesh
    0.09
     mist
    0.09
     Hawkins
    0.09
    iliar
    0.08
     görmek
    0.08
    qrst
    0.08
    terr
    0.08
    Activations Density 0.041%

    No Known Activations