© 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. 31945
    Prev
    Next
    INDEX
    Explanations

    feminist artist women's names

    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
     aff
    -0.11
    ä¸Ĭæľī
    -0.08
    æ©Ħæ¦Ħ
    -0.08
    åī¯å±Ģéķ¿
    -0.08
    çļĦéĩį大
    -0.08
    _rc
    -0.08
    ison
    -0.08
    bugs
    -0.08
    æĴĤ
    -0.08
    åī¯æľ¬
    -0.08
    POSITIVE LOGITS
    å·¾
    0.11
    ä½ĥ
    0.10
    å¦ĩèģĶ
    0.10
    奴éļ¶
    0.10
    æľīæĿ¡ä»¶çļĦ
    0.09
    oise
    0.09
     Woman
    0.09
     Ñģпин
    0.09
    æĸ·
    0.09
    篾
    0.09
    Activations Density 0.087%

    No Known Activations