© 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. 29774
    Prev
    Next
    INDEX
    Explanations

    what would would not

    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
    请æĤ¨
    -0.11
    请éĹ®
    -0.11
    æĤ¨çļĦ
    -0.11
    è®°å¾Ĺ
    -0.10
    iniz
    -0.10
    åı¯ä»¥è¯´
    -0.10
    æĤ¨å¥½
    -0.10
    æ¶ĤæĬ¹
    -0.10
    åĩ¹
    -0.10
    è«ĭæĤ¨
    -0.10
    POSITIVE LOGITS
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    æŃ¤äºº
    0.09
    è¿ĺä¸įå¦Ĥ
    0.09
    å¿ħé¡»è¦ģ
    0.09
    ait
    0.08
     expedition
    0.08
    è¿Ļ家åħ¬åı¸
    0.08
    eyer
    0.08
     Bos
    0.08
    ools
    0.08
    Activations Density 0.048%

    No Known Activations