© 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. 924
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    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
    /if
    -0.09
     Budd
    -0.09
    asley
    -0.09
    éĢŁåº¦å¿«
    -0.09
    ç¡«
    -0.08
    loe
    -0.08
    æ£
    -0.08
    åIJĪãĤıãģĽ
    -0.08
    èĩ
    -0.08
    ä¸ĸ家
    -0.08
    POSITIVE LOGITS
    çļĦ人éĥ½
    0.08
    ãĥ¥ãĥ¼
    0.08
    以ä¸ĬçļĦ
    0.08
    责任åĪ¶
    0.08
    å®Įç¾İçļĦ
    0.08
    ahead
    0.08
    ulta
    0.08
    éĥ½ä¸įçŁ¥éģĵ
    0.08
    æķĽ
    0.08
     probably
    0.08
    Activations Density 0.045%

    No Known Activations