© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26199
    Prev
    Next
    INDEX
    Explanations

    integrated circuit design and naming

    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
    Negative Logits
    eri
    -0.09
    brig
    -0.09
    ç¦ģ
    -0.09
    æĥħ
    -0.09
    åij¼åIJ¸
    -0.09
    awy
    -0.08
    æĪĹ
    -0.08
    幸
    -0.08
    åľ¨ä¸Ĭæµ·
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.09
    ä¿¡å¿ĥ
    0.09
     szy
    0.09
    åijĹ
    0.08
    è¹Ī
    0.08
    çľģéĴ±
    0.08
    eshire
    0.08
    alted
    0.08
    ä¾Ľç»Ļ
    0.08
    çĦļ
    0.08
    Activations Density 0.173%

    No Known Activations