© 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. 51717
    Prev
    Next
    INDEX
    Explanations

    compared to

    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
    åºĵéĩĮ
    -0.11
    å¤ĸæı´
    -0.10
    ä¸Ģåı£æ°Ķ
    -0.10
    undry
    -0.10
    å°±æĺ¯åĽłä¸º
    -0.09
    è¯ŀ
    -0.09
    æľĪä¸Ń
    -0.09
    讣
    -0.09
    æĶ»åĬ¿
    -0.09
    å¸IJåı·
    -0.09
    POSITIVE LOGITS
    亲
    0.08
    å¦Ĥæŀľæĺ¯
    0.08
    親
    0.07
    inth
    0.07
     Rus
    0.07
    justice
    0.07
    è¶Ĭé«ĺ
    0.07
    æĺĵäºİ
    0.07
     Lite
    0.07
    (bp
    0.07
    Activations Density 0.099%

    No Known Activations