© 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. 60834
    Prev
    Next
    INDEX
    Explanations

    too much, too little

    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
     Gardner
    -0.10
    å°ı康
    -0.09
     гол
    -0.09
    åģļèµ·
    -0.08
    å·¦åı³
    -0.08
    ãģŀ
    -0.08
    ë²Į
    -0.08
    UILDER
    -0.08
     FITNESS
    -0.08
    lm
    -0.08
    POSITIVE LOGITS
    ä¸įå¤Ł
    0.15
    è¿ĺä¸įå¤Ł
    0.14
    åĬĽåº¦
    0.13
     insufficient
    0.11
    çİ°è¡Į
    0.11
    éķĩ
    0.10
    å«Į
    0.10
    太å°ij
    0.10
    æĪijçľĭ
    0.09
    åĽ´çĿĢ
    0.09
    Activations Density 0.049%

    No Known Activations