© 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. 59242
    Prev
    Next
    INDEX
    Explanations

    blog posts and eBooks

    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
    pus
    -0.10
    建档
    -0.08
    pu
    -0.08
     marginalized
    -0.08
    oo
    -0.08
     ll
    -0.08
    hl
    -0.08
     History
    -0.08
    dst
    -0.08
    ml
    -0.08
    POSITIVE LOGITS
    æ´ŀå¯Ł
    0.12
    edata
    0.10
    èŀįåIJĪ
    0.10
    æĪĹ
    0.09
    èĹIJ
    0.09
    帮åĬ©ä¼ģä¸ļ
    0.09
     webinar
    0.09
     Symphony
    0.09
    RICS
    0.09
    >Data
    0.09
    Activations Density 0.127%

    No Known Activations