© 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. 597
    Prev
    Next
    INDEX
    Explanations

    extraordinary qualities or achievements

    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
    cken
    -0.09
    alue
    -0.09
    åĨµ
    -0.09
    æĤ²è§Ĥ
    -0.09
    缸åħ³æĶ¿çŃĸ
    -0.08
    è¿Łè¿Ł
    -0.08
    anners
    -0.08
    积æŀģå¼Ģå±ķ
    -0.08
    idd
    -0.08
    gow
    -0.08
    POSITIVE LOGITS
    æĥĬ人
    0.11
    ä¸ĢåĽ¢
    0.11
    èĭij
    0.10
     feats
    0.10
    å¥ĩ迹
    0.10
     Rt
    0.09
    akra
    0.09
    佩æľį
    0.09
     amount
    0.09
    ingly
    0.09
    Activations Density 0.058%

    No Known Activations