© 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. 27442
    Prev
    Next
    INDEX
    Explanations

    code and company names

    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
    åIJij社ä¼ļ
    -0.10
    殿ä¸ĭ
    -0.10
    究竣æĺ¯
    -0.09
    绵
    -0.09
    uring
    -0.09
    /sample
    -0.08
    æ®Ĭ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    åħį
    -0.08
    ä½ķåĨµ
    -0.08
    POSITIVE LOGITS
    æĸ°éĹ»
    0.09
    çļĦæ¶Īæģ¯
    0.09
    è¦ģéĹ»
    0.09
    缸åħ³æĸ°éĹ»
    0.09
    news
    0.09
    快讯
    0.09
    .News
    0.09
    markup
    0.09
    åªĴä½ĵæĬ¥éģĵ
    0.09
    inesis
    0.09
    Activations Density 0.008%

    No Known Activations