© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    post graduate medical training

    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
    olls
    -0.10
    çĤ¹äºĨ
    -0.09
    ngine
    -0.09
    èĹī
    -0.09
    hind
    -0.09
    åħ¬å¼Ģ课
    -0.08
    eton
    -0.08
    æĪŁ
    -0.08
    åħ³å¿ĥ
    -0.08
    çķĻåѦ
    -0.08
    POSITIVE LOGITS
    éĤĪ
    0.10
    åľ³
    0.10
    ç»ĵæĿŁåIJİ
    0.10
    /post
    0.10
    çĨł
    0.10
    åŁºåľ°
    0.09
    china
    0.09
    æĬ¡
    0.09
    墩
    0.09
    æ¸ł
    0.08
    Activations Density 0.024%

    No Known Activations