© 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. 55785
    Prev
    Next
    INDEX
    Explanations

    fundamental data analyst

    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
    åıł
    -0.08
    ç¼ĺ
    -0.08
    COLUMN
    -0.08
    пÑĥÑĤ
    -0.08
    æĪ¿
    -0.08
    æıĨ
    -0.08
     Coc
    -0.08
    Church
    -0.08
    鸡
    -0.08
    å·¥ä½ľæĬ¥åijĬ
    -0.08
    POSITIVE LOGITS
     ХоÑĤ
    0.10
    çķª
    0.10
    ä¸įæĽ¾
    0.09
    UNET
    0.09
    æ¯ıå¹´éĥ½
    0.09
    \\.
    0.09
    æĥħæĬ¥
    0.09
    _sector
    0.09
    èĬĴæŀľ
    0.09
    åIJ¹
    0.09
    Activations Density 0.188%

    No Known Activations