© 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. 6598
    Prev
    Next
    INDEX
    Explanations

    Medicaid, Medi-Cal, OAuth, EMS

    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
    edList
    -0.11
    ãģĵãģ¨
    -0.10
    们
    -0.10
    媳å¦ĩ
    -0.10
    ä¹ŁçŁ¥éģĵ
    -0.10
    LER
    -0.10
    obic
    -0.09
    ç¢Ľ
    -0.09
    íŀĪ
    -0.09
    æĥķ
    -0.09
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////
    0.10
    lek
    0.09
    enticator
    0.09
    iot
    0.09
    ина
    0.09
    çĶ¨è½¦
    0.09
    ordan
    0.08
    /o
    0.08
    ä¸įä¸Ĭ
    0.08
    æĢ¿
    0.08
    Activations Density 0.005%

    No Known Activations