© 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. 762
    Prev
    Next
    INDEX
    Explanations

    ladies and gentlemen

    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
    æīįåıijçİ°
    -0.10
    åijĹ
    -0.10
    pei
    -0.10
    好åĩłä¸ª
    -0.10
    è®©æĽ´å¤ļ
    -0.10
    å¤įåIJĪ
    -0.09
    æ´¾
    -0.09
    ä¿İ
    -0.09
    ä»įå°Ĩ
    -0.09
    æľ¦èĥ§
    -0.09
    POSITIVE LOGITS
    stell
    0.10
    vos
    0.09
    çķľ
    0.09
    åħ±å»º
    0.08
    agt
    0.08
    åIJĮå¿Ĺ们
    0.08
    stations
    0.08
    adies
    0.08
    诸
    0.08
     воÑĤ
    0.08
    Activations Density 0.024%

    No Known Activations