© 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. 29559
    Prev
    Next
    INDEX
    Explanations

    judge, jury, panel, scores

    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
    æĹ©æĻļ
    -0.10
    chip
    -0.09
    CHIP
    -0.09
     Cros
    -0.09
    éĢĤ度
    -0.09
    _owned
    -0.09
    åį°
    -0.09
    é¢Ħè§ģ
    -0.08
     chip
    -0.08
    Chip
    -0.08
    POSITIVE LOGITS
    è¯Ħå§Ķ
    0.28
    è¯Ħ审
    0.21
    è£ģåĪ¤
    0.20
    è¯ĦåĪ¤
    0.18
     jury
    0.18
    çĤ¹è¯Ħ
    0.17
    è¯Ħå®ļ
    0.17
    è¯Ħè®®
    0.16
     judges
    0.16
    è¯Ħæ¯Ķ
    0.16
    Activations Density 0.127%

    No Known Activations