© 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. 1300
    Prev
    Next
    INDEX
    Explanations

    just in case, and yet

    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
    <!--[
    -0.10
    esco
    -0.10
    ä¸Ģ次æĢ§
    -0.10
    é©¿ç«Ļ
    -0.09
    isodes
    -0.09
    ä»·æł¼ä¸Ĭ涨
    -0.09
    isode
    -0.09
    ä¸ŃæľĢ
    -0.09
    èĩªå¦Ĥ
    -0.09
    ç°ĭ
    -0.09
    POSITIVE LOGITS
    7
    0.08
    æ²®
    0.08
    4
    0.08
    à¸Ńล
    0.08
    ä¹ħ
    0.08
    6
    0.08
    tics
    0.08
    0
    0.08
    erva
    0.08
    5
    0.07
    Activations Density 0.005%

    No Known Activations