© 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. 57322
    Prev
    Next
    INDEX
    Explanations

    ronald and ron names

    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
    ivity
    -0.09
    uates
    -0.09
    plied
    -0.09
    åĴĦ
    -0.08
    tabs
    -0.08
     hẳn
    -0.08
    çĹ¢
    -0.08
     تÙħاÙħ
    -0.08
    оÑĤ
    -0.08
    <?=
    -0.08
    POSITIVE LOGITS
    ald
    0.12
    leigh
    0.10
    arth
    0.09
    ../../../
    0.09
    ships
    0.09
    è¶ĬæĿ¥è¶Ĭé«ĺ
    0.09
    nie
    0.09
    cep
    0.09
    itude
    0.09
    aceous
    0.09
    Activations Density 0.013%

    No Known Activations