© 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. 56623
    Prev
    Next
    INDEX
    Explanations

    Maasai, Bhutan, Louboutin

    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
     меÑĢ
    -0.10
    æĽ²æĬĺ
    -0.10
    ç°ª
    -0.09
    çĵ
    -0.09
    说æĺİ书
    -0.09
    chu
    -0.09
    ÑĤен
    -0.09
    лаг
    -0.09
    ä¸įæĸŃæıIJé«ĺ
    -0.08
    åIJĮå¿Ĺ们
    -0.08
    POSITIVE LOGITS
    ãĤ§
    0.08
    亢
    0.08
    allo
    0.08
    кеÑĢ
    0.08
    诡å¼Ĥ
    0.08
    çĥ¦
    0.08
    ãĥ¥ãĥ¼
    0.08
     Handy
    0.08
    éĺ³åı°
    0.08
    าย
    0.08
    Activations Density 0.003%

    No Known Activations