© 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. 63103
    Prev
    Next
    INDEX
    Explanations

    sickle cell disease or myopia

    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
    aat
    -0.09
    èĮ§
    -0.09
     pilgr
    -0.09
    èĻİ
    -0.08
    çIJı
    -0.08
    fried
    -0.08
     mech
    -0.08
    Lab
    -0.08
    ignum
    -0.08
    nable
    -0.07
    POSITIVE LOGITS
    åŁķ
    0.11
    æĮĸæİĺ
    0.11
    èµ°åIJij
    0.11
     пÑĢож
    0.10
    aste
    0.10
    ä¸įæĺ¯ä¸Ģ个
    0.09
    ÅŁtır
    0.09
    æĬĺèħ¾
    0.09
    inery
    0.09
    irty
    0.09
    Activations Density 0.004%

    No Known Activations