© 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. 6968
    Prev
    Next
    INDEX
    Explanations

    medical records

    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
    /stretch
    -0.08
    insky
    -0.08
    浸
    -0.08
    å¼ķ
    -0.08
    omid
    -0.08
    utch
    -0.08
     zg
    -0.08
    çij
    -0.07
     bench
    -0.07
    éľľ
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.12
    воÑĢ
    0.10
     bó
    0.10
    大åħ¨
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    èµ°åĩºåİ»
    0.09
     Sinn
    0.09
    好çľĭ
    0.09
    aint
    0.09
    èľĤ
    0.09
    Activations Density 0.196%

    No Known Activations