© 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. 27550
    Prev
    Next
    INDEX
    Explanations

    much more

    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
    NER
    -0.10
    ä¸įåĩº
    -0.10
    pany
    -0.09
    鬼
    -0.09
    æ¯Ķè¾ĥé«ĺ
    -0.08
    utable
    -0.08
    ettle
    -0.08
    æĺ¯æ¯Ķè¾ĥ
    -0.08
    ä¸įçĶ±
    -0.08
    ç»ıæŁ¥
    -0.08
    POSITIVE LOGITS
    ä¸įæŃ¢
    0.15
    ä¸įä»ħä»ħæĺ¯
    0.15
    ä¸įä»ħä»ħ
    0.14
     beyond
    0.13
    ä¸įä»ħå¦ĤæѤ
    0.13
    ä¸įåıªæĺ¯
    0.12
    æĽ´å¤ļ
    0.11
    Beyond
    0.11
    çĶļ
    0.11
    äºĽä»Ģä¹Ī
    0.11
    Activations Density 0.074%

    No Known Activations