© 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. 20109
    Prev
    Next
    INDEX
    Explanations

    level or number of

    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
    them
    -0.09
    ays
    -0.09
    tery
    -0.09
     them
    -0.08
    æķĻä¼ļ
    -0.08
    æīįæľī
    -0.08
     каждого
    -0.08
     others
    -0.08
    æĸ°çļĦä¸Ģ
    -0.08
    lli
    -0.08
    POSITIVE LOGITS
    æ°ĶåĬ¿
    0.09
    çļĦçĶŁåij½
    0.09
    neau
    0.09
    çļĦçŁ¥è¯Ĩ
    0.09
    æºIJæºIJ
    0.09
    åľ¨ç¾İåĽ½
    0.09
    ramer
    0.09
    ä¸ĢçĽ´ä»¥æĿ¥
    0.09
    InBackground
    0.09
    åħ¥å¢ĥ
    0.09
    Activations Density 0.241%

    No Known Activations