© 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. 16876
    Prev
    Next
    INDEX
    Explanations

    software, theater, STEM, computer

    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
    vro
    -0.09
    æ³±
    -0.09
    ä¸ĭåįĬ
    -0.09
    ürü
    -0.09
    åĨ³çŃĸéĥ¨ç½²
    -0.09
    åıªè¦ģä½ł
    -0.09
    åIJIJ
    -0.09
    Fine
    -0.09
    stead
    -0.09
    è¹Ī
    -0.09
    POSITIVE LOGITS
    ä¸Ģåı·
    0.11
    ä¹ĭæĺŁ
    0.09
    æ³°
    0.08
    éľīç´ł
    0.08
    æĸ¯åŁº
    0.08
    ком
    0.08
    é¢ijéģĵ
    0.08
    TEAM
    0.08
     Zimmerman
    0.08
    KIT
    0.08
    Activations Density 0.983%

    No Known Activations