© 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. 61913
    Prev
    Next
    INDEX
    Explanations

    online payments and credit cards

    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
    ayout
    -0.10
    åĨ³èĥľ
    -0.09
    çľ¼çIJĥ
    -0.09
    æłī
    -0.09
    解读
    -0.09
    åºķæ°Ķ
    -0.09
    èĿĮ
    -0.08
    èݺ
    -0.08
     Pills
    -0.08
    çªł
    -0.08
    POSITIVE LOGITS
    çļĦ身份
    0.09
    acer
    0.09
    egin
    0.08
    身份
    0.08
    å½ĵæĪij们
    0.08
    COOKIE
    0.08
    عط
    0.07
    aldo
    0.07
    æİ¥åħ¥
    0.07
    æĮŀ
    0.07
    Activations Density 0.059%

    No Known Activations