© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 2045
    Prev
    Next
    INDEX
    Explanations

    residency program

    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
    该éĻ¢
    -0.09
    è¯¥æł¡
    -0.09
    å¼ij
    -0.08
    sembly
    -0.08
    ä»ĸå°±
    -0.08
    ä»ĸ们
    -0.08
    æľ¬ç§ijçĶŁ
    -0.08
    piel
    -0.08
    é«ĺå±Ĥ次
    -0.08
    ä»ĸåľ¨
    -0.08
    POSITIVE LOGITS
    大大å°ıå°ı
    0.10
    äºĨæĪijçļĦ
    0.09
    æĪijèĥ½
    0.09
    éŃĶ
    0.09
    çģ«çĤ¬
    0.08
    大éĥ¨åĪĨ
    0.08
    .ico
    0.08
    顺
    0.08
    åľ¨åħ¨åĽ½
    0.08
    Ø·ÙĪØ±
    0.08
    Activations Density 0.148%

    No Known Activations