© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12068
    Prev
    Next
    INDEX
    Explanations

    Medicare programs and patients

    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
    æ°¨éħ¸
    -0.10
    åĿļåĽº
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    çªł
    -0.09
    åħļåĴĮæĶ¿åºľ
    -0.09
    çľģæķĻèĤ²
    -0.09
    çģ£
    -0.09
    çļĦåĬªåĬĽ
    -0.08
     Bieber
    -0.08
    ride
    -0.08
    POSITIVE LOGITS
    .gov
    0.10
    oodle
    0.10
    åİŁåĪĽ
    0.09
    èĢģåħµ
    0.09
    -Benz
    0.09
    ëł¹
    0.09
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.09
    ино
    0.09
    /commons
    0.08
     plunge
    0.08
    Activations Density 0.012%

    No Known Activations