© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9354
    Prev
    Next
    INDEX
    Explanations

    requires or needs

    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
    ä¹ĥèĩ³
    -0.09
    çŁ¥æĻĵ
    -0.09
    æľīæŶ
    -0.08
    orda
    -0.08
    สะ
    -0.08
    zag
    -0.08
    å´¿
    -0.08
    å¤ļäºĨ
    -0.08
    çļĦåĬªåĬĽ
    -0.08
     Bru
    -0.08
    POSITIVE LOGITS
    _gid
    0.09
    requ
    0.09
    ç¥Ŀè´º
    0.09
    éļĪ
    0.09
    éģģ
    0.09
    ä¸Ģä¸ĭåŃIJå°±
    0.09
    çī¹æ´¾
    0.09
     requiring
    0.09
    ç»Ļä½ł
    0.08
    åıĸèĥľ
    0.08
    Activations Density 0.346%

    No Known Activations