© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38257
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases

    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
    寥
    -0.09
    è´¿èµĤ
    -0.09
    itti
    -0.09
    海峡
    -0.09
    ois
    -0.08
    å°ijäºĨ
    -0.08
     Wal
    -0.08
    arme
    -0.08
    æİĴ污
    -0.08
     suicides
    -0.08
    POSITIVE LOGITS
    .blogspot
    0.10
    åĭĸ
    0.09
    çĬ¶åĨµ
    0.09
     underlying
    0.09
    æĥ°
    0.08
    åıijçĶµæľº
    0.08
    ync
    0.08
     koÅŁ
    0.08
    èĥ½ä½¿
    0.08
     Quest
    0.08
    Activations Density 0.121%

    No Known Activations