© 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. 3024
    Prev
    Next
    INDEX
    Explanations

    scholarship offers

    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
    éĤĪ
    -0.09
    大èĩ´
    -0.08
    åī¿
    -0.08
    æµĩæ°´
    -0.08
    atings
    -0.08
    iator
    -0.08
    ä¹ħ
    -0.08
    ertz
    -0.08
    exus
    -0.08
    亥
    -0.08
    POSITIVE LOGITS
     Redistribution
    0.10
    ILI
    0.09
    çľ¯
    0.09
    ILA
    0.09
    åħ¥åѦ
    0.09
    ÑģÑĤи
    0.08
    èģĮ
    0.08
    æ°ĵ
    0.08
     Crusher
    0.08
    iman
    0.08
    Activations Density 0.029%

    No Known Activations