© 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. 62567
    Prev
    Next
    INDEX
    Explanations

    want 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
    ush
    -0.10
    ä¸ĢåIJij
    -0.09
    éļ¾å¾Ĺ
    -0.09
    åŃĶéĽĢ
    -0.08
    çıįæĥľ
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
     Conce
    -0.08
    adm
    -0.08
    åįĹæ²Ļ
    -0.08
     Torres
    -0.08
    POSITIVE LOGITS
    åIJ¬åIJ¬
    0.09
    åĵŃäºĨ
    0.09
    æĪijçİ°åľ¨
    0.09
    è°Īè°Ī
    0.09
    åĪĴ
    0.09
    æ¯ı人
    0.09
    AILS
    0.08
    对æĪij们
    0.08
    /close
    0.08
    inus
    0.08
    Activations Density 0.063%

    No Known Activations