© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21546
    Prev
    Next
    INDEX
    Explanations

    protein and diet related terms

    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
    æĬ±
    -0.09
     Sept
    -0.09
    å¼¥
    -0.08
    å¼łåħĪçĶŁ
    -0.08
    éĹ½
    -0.08
    æĮĩçĶ²
    -0.08
    æ®ĵ
    -0.08
     RVA
    -0.08
    æŃ£
    -0.08
     Reform
    -0.08
    POSITIVE LOGITS
    宪
    0.10
    æŀľ
    0.09
    æŃ¤äºº
    0.09
    ä¸ĢæĹ¥
    0.09
    å¥ĩå¼Ĥ
    0.09
    çĶŁæ´»ä¹łæĥ¯
    0.09
     diá
    0.09
    奥巴
    0.09
    ç§ijåѦåıijå±ķ
    0.09
    è¿Ļä¸ªåľ°åĽ¾
    0.09
    Activations Density 0.256%

    No Known Activations