© 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. 60561
    Prev
    Next
    INDEX
    Explanations

    compensate or alleviate

    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
    èĢĥéªĮ
    -0.09
    Ñģад
    -0.09
    AAC
    -0.08
    嵩
    -0.08
    incer
    -0.08
    à¹Ĥà¸ļ
    -0.08
     Surrey
    -0.08
     Assist
    -0.08
     Wat
    -0.08
    çķª
    -0.08
    POSITIVE LOGITS
    弥补
    0.31
    å¡«è¡¥
    0.21
     compens
    0.18
    è¡¥åģ¿
    0.17
     compensate
    0.17
    æĮ½æķij
    0.16
    åħĭæľį
    0.16
    è¡¥
    0.16
    çºłæŃ£
    0.16
    æĬµå¾¡
    0.16
    Activations Density 0.344%

    No Known Activations