© 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. 572
    Prev
    Next
    INDEX
    Explanations

    father of

    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
    å§Ķ书记
    -0.11
    adh
    -0.10
    æĬĬèĩªå·±çļĦ
    -0.10
    æĬĬèĩªå·±
    -0.09
    ERVE
    -0.09
     зÑĢениÑı
    -0.09
    å°¼äºļ
    -0.09
    åıijçİ°èĩªå·±
    -0.09
    arda
    -0.08
     Scalars
    -0.08
    POSITIVE LOGITS
    hood
    0.13
    less
    0.12
    loquent
    0.10
    LESS
    0.10
    çħĮ
    0.10
    æĥħ人
    0.10
     rock
    0.09
    å±¥è¡Į
    0.09
    éĶı
    0.09
    fs
    0.08
    Activations Density 0.083%

    No Known Activations