© 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. 63928
    Prev
    Next
    INDEX
    Explanations

    larger-than-life, outspoken, eccentric

    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
    door
    -0.10
    å¿ħè¦ģ
    -0.09
    æľĢç¾İçļĦ
    -0.09
    flix
    -0.08
    åįıå®ļ
    -0.08
    å°±æĺ¯ä¸Ģ个
    -0.08
    ambient
    -0.08
    rites
    -0.08
    asic
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
    ä½ľèĢħæľ¬äºº
    0.12
    ä½Ĩå®ĥ
    0.11
     affirmation
    0.09
    çĥŁèĬ±
    0.09
     Widgets
    0.09
    ä¸Ńæŀ¢
    0.08
     widgets
    0.08
    ลà¸Ń
    0.08
    ä½Ĩä»İ
    0.08
    ä½Ĩ她
    0.08
    Activations Density 0.023%

    No Known Activations