© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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
     bass
    -0.08
    è¿Ļ家ä¼Ļ
    -0.08
     Bass
    -0.08
    æ£ł
    -0.08
    æıIJä¾ĽæĽ´å¤ļ
    -0.08
    é¦Ī
    -0.08
    BCM
    -0.08
    åħ¨éķ¿
    -0.08
    æľ¬ç«Ļ
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    POSITIVE LOGITS
    ä¸įåľ¨
    0.12
    å¤Ħåľ¨
    0.11
    åľ¨ä¸Ģèµ·
    0.10
    å¤Ħäºİ
    0.10
    è¿ľç¦»
    0.10
    åľ¨ä¸Ģ个
    0.09
    æĶ¾åľ¨
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    身å¤Ħ
    0.09
    åľ¨å®¶
    0.09
    Activations Density 0.105%

    No Known Activations