© 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. 54374
    Prev
    Next
    INDEX
    Explanations

    medical and biological conditions

    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
    uai
    -0.09
    ä¼ı
    -0.09
     Rubin
    -0.08
    æ°ĸ
    -0.08
    OfString
    -0.08
    ä¾µ
    -0.08
    讲è¯Ŀ
    -0.08
    ((_
    -0.08
    æ¡ħ
    -0.08
    -vs
    -0.08
    POSITIVE LOGITS
    ï¼Ī
    0.16
     (
    0.16
     (↵
    0.11
     ï¼Ī
    0.10
    áĪº
    0.10
    (
    0.10
    (↵
    0.09
     ()
    0.09
    isko
    0.08
    oho
    0.08
    Activations Density 0.869%

    No Known Activations