© 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. 754
    Prev
    Next
    INDEX
    Explanations

    academic and research abbreviations

    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
    _UL
    -0.09
    dle
    -0.09
     ula
    -0.08
    ãģĶ
    -0.08
    Caught
    -0.08
    å¼ıçļĦ
    -0.08
     sof
    -0.07
     Yas
    -0.07
    çĶ©
    -0.07
    xes
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.17
    åı«åģļ
    0.10
    åıĪ称
    0.09
    åħ¨æĸ°çļĦ
    0.09
    èĨı
    0.09
    é¹ħ
    0.09
    ä¸ĭ称
    0.09
    ä»Ģä¹Īåij¢
    0.09
    åĶĽ
    0.09
     ì§Ħ
    0.09
    Activations Density 0.392%

    No Known Activations