© 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. 58306
    Prev
    Next
    INDEX
    Explanations

    diabetes and cardiovascular disease

    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
    åĨ¤
    -0.10
    é¢ħ
    -0.10
    -earth
    -0.10
    æ£ļ
    -0.10
    é£Ļ
    -0.09
    å¬
    -0.09
    efs
    -0.09
    å¦į
    -0.08
     Cove
    -0.08
    -minus
    -0.08
    POSITIVE LOGITS
    èĥ°
    0.13
    ç³ĸå°¿
    0.13
    è¡Ģç³ĸ
    0.13
    ç³ĸå°¿çĹħ
    0.11
     diabetic
    0.11
     insulin
    0.11
     glucose
    0.10
     Diabetes
    0.10
     diabetes
    0.10
     ÑģаÑħаÑĢ
    0.09
    Activations Density 0.397%

    No Known Activations