© 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. 54944
    Prev
    Next
    INDEX
    Explanations

    eating habits and delicious foods

    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
    å¼ķæĿ¥
    -0.09
    afil
    -0.09
     Voy
    -0.09
    asm
    -0.09
    åįĵ
    -0.08
    èģĶç³»æĪij们
    -0.08
    è¢Ĥ
    -0.08
    umu
    -0.08
    ç¥ŀæĥħ
    -0.08
     Hoff
    -0.08
    POSITIVE LOGITS
    ä¹°çļĦ
    0.09
    udies
    0.09
    æºľ
    0.08
    .shop
    0.08
    buyer
    0.08
     bub
    0.08
     mess
    0.08
    /dc
    0.08
    ä¸Ģçľ¼
    0.08
    ascade
    0.07
    Activations Density 0.039%

    No Known Activations