© 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. 1267
    Prev
    Next
    INDEX
    Explanations

    only, it, no

    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
    æµ®
    -0.11
    个åĪ«
    -0.10
    å¤ĸå½¢
    -0.09
    qp
    -0.09
    éķ¶åµĮ
    -0.09
    yt
    -0.08
    plex
    -0.08
    RATION
    -0.08
    yk
    -0.08
     Lives
    -0.08
    POSITIVE LOGITS
     ë§İ
    0.10
    太å¤ļäºĨ
    0.09
    çļĦæķ°éĩı
    0.09
     غاÙĦب
    0.09
    ä¹Łå°±æĺ¯
    0.09
    èµ°åħ¥
    0.09
    ardi
    0.09
    åİĨç¨ĭ
    0.08
    èµ°è¿Ľ
    0.08
    æºIJæºIJ
    0.08
    Activations Density 0.091%

    No Known Activations