© 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. 47712
    Prev
    Next
    INDEX
    Explanations

    cyrillic programming phrases

    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
    eko
    -0.09
    æ¯įåħ¬åı¸
    -0.08
    UNK
    -0.08
    umo
    -0.08
    åijĬ
    -0.08
    æĹ¢
    -0.08
    ä¿¡æģ¯åĮĸ
    -0.08
    çĶŁçĶŁ
    -0.08
     Leh
    -0.08
     Reload
    -0.08
    POSITIVE LOGITS
    ä¼łåĩº
    0.10
    å¸ĸ
    0.09
    inel
    0.09
    峪
    0.09
    çĢĽ
    0.09
    oul
    0.08
     ÑĨелÑĮÑİ
    0.08
     помоÑīÑĮÑİ
    0.08
    ä¸Ģ个å¤ļ
    0.08
    ERA
    0.08
    Activations Density 0.050%

    No Known Activations