© 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. 29556
    Prev
    Next
    INDEX
    Explanations

    wording and language usage

    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
    erville
    -0.10
    liga
    -0.09
    åIJį
    -0.09
    infra
    -0.08
    راÙĩ
    -0.08
    æĭ³å¤´
    -0.08
    .enc
    -0.08
    Enc
    -0.08
    (enc
    -0.08
     hous
    -0.08
    POSITIVE LOGITS
    æݪ
    0.11
    åı¥åŃIJ
    0.11
    äºĨä¸Ģåı¥
    0.10
    ather
    0.10
     wording
    0.10
    é³ĥ
    0.10
    ured
    0.09
    æĸĩæ¡Ī
    0.09
    ноп
    0.09
    峡
    0.09
    Activations Density 0.040%

    No Known Activations